Formal fuzzy logic: Difference between revisions

From Citizendium
Jump to navigation Jump to search
imported>Giangiacomo Gerla
mNo edit summary
 
(159 intermediate revisions by 8 users not shown)
Line 1: Line 1:
{{subpages}}
{{subpages}}
To be Completed !!
{{TOC|right}}
{{TOC-right}}
=== Introduction ===
'''Formal fuzzy logic''', or "fuzzy logic in narrow sense", is a relatively new chapter of formal logic. Its aim is to represent predicates which are vague in nature as ''big'', ''near'', or ''similar'' (for example), and to formalize the reasonings involving these predicates. The notion of a ''[[fuzzy subset]]'', proposed by L. A. Zadeh since 1965,  plays a crucial role, since a vague predicate is interpreted by a fuzzy subset. In the sequel, we will write "fuzzy logic" instead of "formal fuzzy logic", but notice that in literature the name ''"fuzzy logic"'' comprises a large series of topics based on the notion of a fuzzy subset and which are usually devoted to applications.


We can consider fuzzy logic as an evolution and an enlargement of multi-valued logic since all the definitions and results in the literature on multi-valued logic are also considered in fuzzy logic. There are two basic approaches to fuzzy logic. The first one, proposed by P. Hajek and by a large series of students, is strictly closed to the tradition of multi-valued logic. Indeed the logical consequence operator works on a given classical subset of hypotheses to give the related classical set of logical consequences. Equivalently, the entailment relation is a crisp one. This is obtained, as it is usual in multi-valued logic, once a set of designed truth values is fixed. We call, '' ungraded approach'', in brief ''U-approach'', such a way to face fuzzy logic. Another approach was proposed by J. A. Goguen, J. Pavelka and many authors and it is rather out of line with the tradition of multi-valued logic. Indeed, by referring to the logical consequence operator, this operator works on a given fuzzy subset of hypotheses (the available information) to give the related fuzzy subset of logical consequences. Equivalently, the entailment relation is a fuzzy relation. We call ''graded approach'', in brief '' G-approach'' such a way to face fuzzy logic.
'''Fuzzy [[logic]]''' is a relatively new chapter of [[formal]] logic whose aim is to formalize the reasonings involving predicates that are vague in nature (as an example ''small'', ''near'', ''similar''). An example of such kind of reasoning is


As in multi-valued logic, the starting point is a ''valuation structure'', i.e. a bounded lattice ''L'' whose elements are interpreted as truth degrees. SUch a lattice is equipped with suitable operations to interpret the logical connectives. Usually one considers two operations <math>\otimes </math> and <math>\rightarrow </math> to interpret the conjunction and implication connectives. An important class of valuation structures is furnished by the interval [0,1] with a continuous [[triangular norm]] <math> \otimes </math>, i.e. a continuous, associative, commutative, order preserving operation such that x <math>\otimes</math> 1 = 1. Moreover, <math>\rightarrow </math> is the related residuation operation, i.e. one sets x → y = sup{z | x <math>\otimes </math>z ≤ y} (see Hájek 1998, Novák et al. 1999 and Gottwald 2005). Several authors consider also logical constants to denote rational truth values. Once a valuation structure is fixed, the semantics of the corresponding propositional calculus is defined in a truth-functional way as usual. The semantics of the corresponding first order fuzzy logic is defined by the notion of fuzzy-interpretation as follows.
: ''If a tomato is red, then the tomato is ripe. Since this tomato is very red, this tomato is very ripe.''


Further examples of reasonings involving vague predicates are in the item ''[[Paradoxes and fuzzy logic]]'' and in the section ''Fuzzy logic with no truth-functional semantics''. The main tool for fuzzy logic is the notion of a ''[[fuzzy subset]]'', since a vague predicate is interpreted by a fuzzy subset. Notice that in literature the name ''"fuzzy logic"'' also denotes a large series of topics based on an informal usage of the notion of a fuzzy subset, and which are usually devoted to applications.


'''Definition. ''' A ''fuzzy interpretation'' of a first order language is a pair (''D'',''I'') such that ''D'' is a nonempty set and ''I'' a map associating (as in the classical case) every n-ary operation name ''h'' with an n-ary operation ''I(h)'' : ''D''<sup>n</sup> → ''D'' and every constant ''c'' with an element ''I''(''c'') in ''D''. Moreover, I associates every n-ary predicate name ''r'' with an ''n''-ary fuzzy relation ''I(r)'' : ''D''<sup>n</sup> → ''L'' in ''D''.  
As a matter of fact, fuzzy logic is an evolution and an enlargement of [[multi-valued logic]] since all the definitions and results in the literature on multi-valued logic are also considered in fuzzy logic. In particular, as in multi-valued logic, the starting point is a fixed ''valuation structure'', i.e. a bounded [[lattice (order)|lattice]] ''L'' equipped with suitable operations to interpret the logical connectives. The minimum 0 means ''''False'''', the maximum 1 means ''''True'''', the remaining elements are interpreted as intermediate truth values. The following is the main class of valuation structures (see Hájek 1998, Novák et al. 1999 and Gottwald 2005) corresponding to the connectives <math>\wedge</math> and <math>\rightarrow </math>.




Then, the only difference with classical logic is that the interpretation of an ''n''-ary predicate symbol is an ''n''-ary fuzzy relation in ''D''. This enables us to represent properties which are "vague" in nature. Given a fuzzy interpretation we can evaluate the formulas as follows where, given a term ''t'', we denote by <math>I(t)</math> the corresponding function we define as in classical logic.
'''Definition.''' A ''standard algebra'' is an algebraic structure ([0,1], ʘ, →, 0,1) where ʘ is a continuous triangular norm, i.e. a continuous, associative, commutative, order preserving operation such that ''x''ʘ1 = 1 and → is the related residuation, i.e. ''x''→''y'' = sup{''z'' | ''x''ʘ''z'' ''y''}.




'''Definition.''' Let (''D,I'') be a fuzzy interpretation and <math>\otimes</math> a triangular norm. Then for every formula α whose free variables are in <math>\{x_1,...x_n\}</math> and <math>d_1,...,d_n</math> in ''D'', we define the truth degree Val<math>(I,\alpha,d_1,...,d_n)</math> by induction as follows
The main examples of standard algebras are obtained by assuming that ʘ is the minimum (Zadeh logic), the usual product (product logic) or that ''x''ʘ''y'' = ''Max{x+y-1,0}'' (Łukasievicz logic). In addition, several authors consider also languages with logical constants to denote rational truth values. Once a valuation structure is fixed, the semantics of the corresponding propositional calculus is defined in a truth-functional way as usual. In first order fuzzy logic the semantics is defined as follows.


Val<math>(I, r(t_1,...,t_p),d_1,...,d_n) = I(r)(I(t_1)(d_1,...,d_n), ..., I(t_p)(d_1,...,d_n))</math>


Val<math>(I,\alpha\wedge \beta,d_1,...,d_n) </math> = Val<math>(I,\alpha,d_1,...,d_n)\otimes </math>Val<math>(I,\beta,d_1,...,d_n) </math>
'''Definition. ''' A ''fuzzy interpretation'' of a first order language is a pair (''D'',''I'') such that ''D'' is a nonempty set and ''I'' a map associating (as in the classical case) every ''n''-ary operation name ''h'' with an ''n''-ary operation in ''D'' and every constant ''c'' with an element ''I''(''c'') in ''D''. Moreover, ''I'' associates every ''n''-ary predicate name ''r'' with an ''n''-ary ''L''-relation ''I''(''r'') : ''D<sup>n</sup>''<math>\rightarrow</math> ''L'' in ''D''.


Val<math>(I,\alpha \Rightarrow \beta, d_1,...,d_n) </math> = Val<math>(I,\alpha~, d_1,...,d_n) \rightarrow</math>Val<math>(I,\beta,d_1,...,d_n)</math>


Val<math>(I,\neg \alpha, d_1,...,d_n,\otimes) = </math> ~ Val<math>(I,\alpha,d_1,...,d_n) </math>
Then the only difference with classical logic is that the interpretation of an ''n''-ary predicate symbol is an ''n''-ary [[fuzzy subset|fuzzy relation]] in ''D''. This enables us to represent properties which are "vague" in nature. Given a fuzzy interpretation we can evaluate the formulas as follows where, given a term ''t'' whose variables are in ''x''<sub>1</sub>,...,''x''<sub>n</sub>, we denote by <math>I(t)</math> the corresponding ''n''-ary function we define as in classical logic.


Val<math>(I,\forall x_i \alpha,d_1,...,d_n,\otimes) = inf_{d\in D}</math>Val<math>(I,\alpha,d_1,...,d_{i-1},d,d_{i+1},...,d_n)</math>.


'''Definition.''' Let (''D,I'') be a fuzzy interpretation, α a formula whose free variables are in ''x''<sub>1</sub>,...,''x''<sub>n</sub> and ''d''<sub>1</sub>,...,''d''<sub>n</sub> elements in ''D''. Then we define the truth degree ''Val''(''I'',α,''d''<sub>1</sub>,...,''d''<sub>n</sub>) by induction as follows :


Observe that in the case ''L'' is not complete it is possible that there is a quantified formula which cannot be evaluated. We call ''safe'' an interpretation such that all the formulas are evaluated. As usual, if α is a closed formula, then its valuation does not depend on the elements <math>d_1,...,d_n</math> and we write Val<math>(I,\alpha)</math> instead of Val<math>(I,\alpha,d_1,...,d_n)</math>. More in general, given any formula α, we denote by Val(I), the valuation of the universal closure of α. To emphasize the dependence on the triangular norm, sometimes we write Val<math>_{\otimes}(I,\alpha,d_1,...,d_n)</math> instead of Val<math>(I,\alpha,d_1,...,d_n)</math>.
:''Val''(''I'', ''r''(''t''<sub>1</sub>,...,''t''<sub>''p''</sub>), ''d''<sub>1</sub>,...,''d''<sub>''n''</sub>) = ''I''(''r'')(''I''(''t''<sub>1</sub>)(''d''<sub>1</sub>,...,''d''<sub>''n''</sub>), ..., ''I''(''t''<sub>''p''</sub>)(''d''<sub>1</sub>,...,''d''<sub>''n''</sub>))


== The ungraded approach ==
:''Val''(''I'',α <math>\wedge</math> β, ''d''<sub>1</sub>,...,''d''<sub>''n''</sub>) = ''Val''(''I'',α,''d''<sub>1</sub>,...,''d''<sub>''n''</sub>)ʘ''Val''(''I'',β,''d''<sub>1</sub>,...,''d''<sub>''n''</sub>)


In the ungraded approach one considers a subset ''Des'' of [0,1] whose elements are called ''designed truth degrees''. The interpretation is that in ''Des'' there are the truth degrees which one considers sufficient to claim the validity of a formula. Since it is natural to admit that if ''x'' is sufficient and y>x, then ''y'' is sufficient, we assume that ''Des'' is an interval in [0,1]. Usually one set ''Des'' = {1}.
:''Val''(''I'',α → β, ''d''<sub>1</sub>,...,''d''<sub>''n''</sub>) = ''Val''(''I'',α, ''d''<sub>1</sub>,...,''d''<sub>''n''</sub>) → ''Val''(''I'',β,''d''<sub>1</sub>,...,''d''<sub>''n''</sub>)


TO BE COMPLETED !!!
:''Val''(''I'',<math>\forall </math> ''x<sub>i</sub>''α, ''d''<sub>1</sub>,...,''d''<sub>''n''</sub>) = ''Inf<sub> dєD</sub>Val''(''I'',α,''d''<sub>1</sub>,...,''d''<sub>''i''-1</sub>,''d'',''d''<sub>''i''+1</sub>,...,''d''<sub>''n''</sub>).


In the case there is a propositional constant ''c<sup>*</sup>'' corresponding to a truth value ''c'', we set


'''Definition'''. Let (''L'',<math>\otimes</math>,<math>\rightarrow</math>, 0, 1) be a valuation structure. Then we call ''fuzzy model'', in brief ''model'', an interpretation (''D,I'') in ([0,1], <math>\otimes</math>, →,0,1). We say that a formula α is ''valid'' in (''D,I'') if Val(I,α) is in ''Des'' and that α is a ''standard tautology'' if it is valid in every model. Let ''T'' be a theory, i.e. a set of sentences, then we say that (''D,I'') is a ''model of T'' if every formula in ''T'' is valid in (''D,I''). We write ''T'' <math>\models</math> α if every model of ''T'' is a model of α. The ''logical consequence operator'' is the map ''Lc'' : {0,1}<sup>F</sup> → {0,1}<sup>F</sup> defined by setting
:''Val''(''I'', ''c<sup>*</sup>'',''d''<sub>1</sub>,...,''d''<sub>''n''</sub>) = ''c''.
''Lc''(''T'') = {α<math> \in</math> F: ''T'' <math>\models</math>α}.


The deduction apparatus in the U-approach is defined by adopting the same paradigm of classical logic, i.e. by a set of logical axioms and suitable inference rules. Such an apparatus enables us to generate, given a (crisp) set of proper axioms, the related (crisp) set of theorems. Unfortunately, one proves that the entailment relation <math>\models</math> is not compact and that the set of standard tautologies is not recursively enumerable. This entails that a completeness theorem is not possible. As an alternative one proposes a different entailment relation related with the variety generated by a given triangular norm.  
Observe that in the case ''L'' is not complete it is possible that a quantified formula cannot be evaluated. We call ''safe'' an interpretation such that all the formulas are evaluated. As usual, if α is a closed formula, then its valuation does not depend on the elements ''d''<sub>1</sub>,...,''d<sub>n</sub>'' and we write ''Val''(''I'',α) instead of ''Val''(''I'',α,''d''<sub>1</sub>,...,''d''<sub>''n''</sub>). More in general, given any formula α, we denote by ''Val''(''I'', α) the valuation of the universal closure of α.


== Two approaches ==
There are two basic approaches to fuzzy logic. The first one, proposed by P. Hajek and followed by Di Nola, Esteva, Gottwald, Godo, Montagna, Mundici and by a large series of students, is very close to the tradition of multi-valued logic. Indeed the deduction apparatus works on a set of hypotheses to give the corresponding set of logical consequences. This is obtained, as it is usual in multi-valued logic, once a set of designed truth values is fixed. We call, ''ungraded approach'' such a way to face fuzzy logic. Another approach was proposed by J. A. Goguen, J. Pavelka, V. Novak, G. Gerla and further authors and it is rather out of line with the tradition of multi-valued logic. Indeed, the deduction apparatus works on a given fuzzy subset of hypotheses (the available information) to give the related fuzzy subset of logical consequences. We call ''graded approach'' such a way to face fuzzy logic.


'''Definition.''' Given a triangular norm <math>\otimes</math>, denote by <math>Varl(\otimes)</math> the class of all linearly ordered algebras in the variety generated by ([0,1], <math>\otimes</math>, →,0,1).  Then a ''<math>Varl(\otimes)-</math>model'' is an interpretation in a valuation algebra belonging to Varl<math>(\otimes)</math>. Given a set ''T'' of formulas and a formula α, we write ''T'' |=<sub>Varl(<math>\otimes</math>)</sub> α provided that every safe Varl(<math>\otimes</math>)-model of ''T'' is a safe Varl<math>\otimes</math>)-model of α. A formula α which is valid in every safe Varl(<math>\otimes</math>)-model is named a ''general tautology''. 
=== The ungraded approach ===
 
 
The resulting logic works well. In fact, by giving suitable notions of logical axiom and inference rules, we can obtain a completeness theorem.  In first order fuzzy logic the general tautologies form a proper subset of the set of standard tautologies.
 
== The graded approach: approximate reasonings ==
 
The graded approach is perhaps closer to the spirit of fuzzy logic. In fact the aim of any logic is to eleborate (uncomplete) information and, in the case of fuzzy logic should be natural to admit an information like ''"the truth values of α is between λ and μ"'', i.e. a constraint on the possible truth value of a formula. Taking in account that for a large class of fuzzy semantics we can split it into the two constraints ''"the truth values of α is greater or equal to λ"'' and ''"the truth value of <math>\neg</math>α is greater or equal to 1-μ"'', we consider the following definitions.
   
   
In the ungraded approach a subset ''Des'' of [0,1] is fixed whose elements are called ''designed truth degrees''. The interpretation is that in ''Des'' there are the truth degrees which one considers sufficient to claim the validity of a formula. Usually one sets ''Des'' = {1}.




'''Definition ''' (''G-approach''). Consider a fuzzy theory ''s'', i.e. a fuzzy subset of formulas. Then we say that a fuzzy interpretation (''D,I'') is a ''model of s'', in brief ''(D,I)'' <math>\models </math>''s'' if Val(I,α) ≥ s(α). The ''logical consequence operator'' is the map ''Lc'' : [0,1]<sup>F</sup> → [0,1]<sup>F</sup> defined by setting
'''Definition'''. Let ([0,1], ʘ, →, 0, 1) be a fixed standard algebra, and α be a formula. Then we say that a fuzzy interpretation (''D,I'') ''satisfies'' α  provided that ''Val''(''I'',α) is a designed value. Let ''T'' be a theory, then (''D,I'') is a ''model of T'' if every formula in ''T'' is satisfied in (''D,I''). We write ''T'' <math>\models</math><sub>ʘ</sub> α if every model of ''T'' satisfies α.  
 
''Lc''(''s'')(α) = Sup{Val(I,α) : (D,I) <math> \models </math>s}.
 
 
Then the meaning of a fuzzy theory ''s'' is that for every sentence α, the value s(α) is a ''constraint"'' on the unknown truth value of α. More precisely s(α) is a lower bound for such a value. Again, the value Lc(s)(α) is a ''"constraint"'' on the unknown truth value of α. As a matter of fact it is the better constraint we can find given the information ''s''.  
 
'''Note'''. We interpret a fuzzy theory ''s'' as a fuzzy subset of (proper) axioms. Now, the word ''"axiom"'' originates from the fact that formal logic was usually considered as a tool for mathematics. In the case of fuzzy logic, which is related with everyday experience, perhaps  expressions as ''"hypothesis"'', ''"assumptions"'', ''"partial information"'', ''"postulate"'' are more adequate.
 
In the graded approach to fuzzy logic a completeness theorem claims that the deduction apparatus is adequate to "calculate" the values of Lc(s) by an effective approximation process. We can obtain such an apparatus by extending the Hilbert's approach as follows.
 
'''Definition.''' A ''fuzzy inference rule'' is a pair ''r'' = (''sy'',''se'') where ''sy'', the ''syntactical part'', is a partial ''n''-ary operation in ''F'' (i.e. an inference rule in the usual sense) and ''se'', the ''semantical part'', is an ''n''-ary joing-preserving operation in [0,1]. An ''evaluated syntax'' is a structure (''la'',''R'') where ''la'' is a fuzzy set of formulas we call ''fuzzy subset of logical axioms'', and ''R'' is a set of fuzzy inference rules.  
 


The meaning of an inference rule ''r'' is:
The deduction apparatus in the ungraded approach is defined by adopting the same paradigm of classical logic, i.e. a ''deduction relation'' <math>\vdash</math> is defined by a suitable set of logical axioms and suitable inference rules. The fuzzy logic defined by ʘ is ''axiomatizable'' provided that a deduction apparatus exists such that <math>\vdash</math> coincides with <math>\models</math><sub>ʘ</sub>. Unfortunately, the main fuzzy logics are not axiomatizable.


- if we are able to prove <math>\alpha_1,...,\alpha_n</math> at degree <math>\lambda_1,...,\lambda_n</math>, respectively


- and we can apply ''sy'' to <math>\alpha_1,...,\alpha_n</math>
'''Theorem.''' In all the main fuzzy logics (in particular in Łukasievicz logic) the entailment relation <math>\models</math><sub>ʘ</sub> is not compact. This entails that these logics are not axiomatizable.


- then we can prove <math>sy(\alpha_1,...,\alpha_n)</math> at degree <math>se(\lambda_1,...,\lambda_n )</math>.
Usually, ''sy''(λ<sub>1</sub>,...,λ<sub>n</sub>) is a product like λ<sub>1</sub><math>\otimes</math>...<math>\otimes</math> λ<sub>n</sub>. As an example, the ''fuzzy Modus Ponens'' is defined by assuming that the domain of ''sy'' is the set {(α, α→β:  α,β are in F}, by setting  ''sy''(α, α→β) = β and by assuming that ''se''(λ,μ) = λ<math>\otimes</math>μ. This rule says that if we are able to prove  α and α →β at degree λ and μ, respectively, then we can prove β at degree λ<math>\otimes</math>μ.
Likewise, the ''fuzzy'' <math>\and</math>''-introduction rule'' is a totally defined rule such that ''sy''(α,β) =  α<math>\and</math>β and ''se''(λ,μ) = λ<math>\otimes</math>μ. This rule says that if we are able to prove α and β at degree λ and μ, respectively, then we can prove α<math>\and</math>β at degree λ<math>\otimes</math>μ.
'''Definition'''. A ''proof'' π of a formula α is a
sequence <math>\alpha_1,...,\alpha_m</math> of formulas such that <math>\alpha_m</math>= α,
together with a sequence of related ''justifications''. This means that, for
every formula <math>\alpha_i</math>, we have to specify whether


i) <math>\alpha_i</math> is assumed as a logical axiom or;
As an attempt to bypass such an obstacle, in the ungraded approach one proposes a different entailment relation related with the variety generated by a given triangular norm.


ii) <math>\alpha_i</math> is assumed as an hypothesis or;


iii) <math>\alpha_i</math> is obtained by a rule (in this case we have to indicate
'''Definition.''' Given a standard algebra ([0,1], ʘ, →,0,1), denote by ''Varl''(ʘ) the class of all linearly ordered algebras in the variety generated by ([0,1], ʘ, →, 0, 1).  Then a ''Varl(ʘ)-interpretation'' is an interpretation in a valuation algebra belonging to ''Varl''(ʘ). Given a set ''T'' of formulas and a formula α, we write ''T'' <math>\models</math><sub>''Varl''(ʘ)</sub> α provided that every safe ''Varl''(ʘ)-model of ''T'' is a safe ''Varl''(ʘ)-model of α.
also the rule and the formulas from <math>\alpha_1,...,\alpha_{i-1}</math> used to
obtain <math>\alpha_i</math>).




The justifications are necessary to valuate the proofs. Indeed, let ''s'' be the fuzzy subset of proper axioms and, for every ''i ≤ m'' denote by π(i) the proof <math>
In such a case, the resulting logic works well. In fact, the following theorem holds true.
\alpha_1,...,\alpha_i</math>. Then the valuation Val(π,s) of π with
respect to ''s'' is defined by induction on ''m'' by setting


<math>Val(\pi ,s) = la(\alpha_m)</math> if <math>\alpha _m</math> is assumed as a logical axiom


<math> Val(\pi ,s) = s(\alpha_m)</math> if <math>\alpha _m</math> is assumed as an hypothesis
'''Theorem'''. In all the main fuzzy logics (in particular in Łukasievicz logic) the entailment relation <math>\models</math><sub>''Varl''(ʘ)</sub> is compact. This is in accordance with the fact that these logics are axiomatizable (provided that they are defined by referring to this relation).


Val(π,s) = <math>se(Val(\pi(i_1),s),...,Val(\pi (i_n),s))</math> if there is a fuzzy rule <math>(sy,se)</math> such that <math>
\alpha_m = sy(\alpha_{i(1)},...,\alpha_{i(n)})</math> with i(1) < m,...,i(n) < m.


Now, unlike the usual deduction systems, in a fuzzy deduction system
'''Criticisms.''' A criticism for the ungraded approach, philosophical in nature, concerns its adequateness to represent the daily reasonings in which vague predicates occur. Moreover the structures in ''Varl''(ʘ) look rather unnatural. For example, in ''Varl''(ʘ) there are structures with infinitesimal truth values. Another criticism is that, while the completeness of [0,1] assures that all the formulas are valuated, in the case we refer to the variety ''Varl''(ʘ), we are forced to admit interpretations for which there are unvaluated formulas.
different proofs of a same formula α may give different contributions to the degree of validity of  α. This suggests setting


D(s)(α)= Sup{Val(π,s)| π ''is a proof of'' α}.
=== The graded approach: approximate reasonings ===


This formula defines an operator, the ''deduction operator'', able to associate every fuzzy theory ''s'' with the fuzzy subset ''D(s) of formulas deduced from s''.  
The aim of any logic is to elaborate (uncomplete) information to obtain more explicit information. Now, in the case of fuzzy logic it is natural to admit an information like ''"the truth values of α is between λ and μ"'', i.e. a constraint on the possible truth value of a formula. Now, observe that if we admit the usual interpretation of the negation, then ''Val''(''I'',α)''≤ λ'' if and only if ''Val''(''I'',<math>\neg</math> α)''≥ 1-μ''. Then we can reduce all the interval constraints to lower bound constraints. In accordance in the graded approach one proposes the following definition.
   
   
'''Definition '''. Consider a fuzzy theory ''s'', i.e. a fuzzy subset of formulas. Then a fuzzy interpretation (''D,I'') is a ''model of s'', in brief (''D,I'') <math>\models </math>'' s'' if ''Val''(''I'',α) ≥ ''s''(α). The ''logical consequence operator'' is the map ''Lc'' : [0,1]<sup>''F''</sup> → [0,1]<sup>''F''</sup> defined by setting


'''Definition.''' A fuzzy logic is ''axiomatizable'' if there is a fuzzy deduction system such that ''Lc = D''.
:''Lc''(''s'')(α) = ''Inf''{''Val''(''I,α'') : (''D,I'') <math> \models </math> ''s''}.


Notice that under some natural hypotheses, a fuzzy propositional logic is axiomatizable if and only if the logical connectives are interpreted by continuous functions (see Gerla 2001). As was shown in Hajek 1998, completeness results for first order fuzzy logic can be find if one adds a constant for every rational value in [0,1].
Equivalently, we can refer to a ''graded entailment relation'' <math> \models </math><sup>λ</sup> by writng ''s'' <math> \models </math><sup>λ</sup> α  where λ = ''Inf''{''Val''(''I,α'') : (''D,I'') <math>\models </math> ''s''}.


== Paradoxes ==
These definitions are in accordance with the fact that ''s'' represents a system of ''"lower bound constraints"'' on the unknown truth value of the formulas. Moreover, ''Lc''(''s'') is the better lower bound constraint we can find given ''s''. In the graded approach we can obtain a deduction apparatus by extending Hilbert's approach as follows.


=== The heap paradox ===
'''Definition.''' A ''fuzzy inference rule'' is a pair ''r'' = (''syn'',''sem'') where ''syn'', the ''syntactical part'', is a partial ''n''-ary operation in ''F'' (i.e. an inference rule in the usual sense) and ''sem'', the ''semantic part'', is an ''n''-ary join-preserving operation in [0,1]. An ''evaluated syntax'' is a structure (''la'',''R'') where ''la'' is a fuzzy set of formulas we call ''fuzzy subset of logical axioms'', and ''R'' is a set of fuzzy inference rules.  
To show an example of approximate reasoning in fuzzy logic we refer to the famous ''"heap paradox"''. Let ''n'' be a natural number and denote by Small(''<u>n</u>'') a sentence whose intended meaning is ''"a heap with n stones is small"'' (''<u>n</u>'' is a numeral to denote ''n''). Then it is natural to assume the validity of the atomic formula Small(1) and, for every ''n'', the validity of Small(''<u>n</u>'') → Small(''<u>n+1</u>'').


On the other hand from these formulas given any natural number ''n'', by applying MP (Modus Ponens) rule several times we can prove that a heap with ''n'' stones is small. Indeed,
Usually, ''n'' = 2 and ''sem''(λ<sub>1</sub>,λ<sub>2</sub>) is a product like λ<sub>1</sub>ʘ λ<sub>2</sub>. As an example, the ''fuzzy Modus Ponens'' is defined by assuming that the domain of ''syn'' is the set {(α, α→β):  α,β are in ''F''}, by setting  ''syn''(α, α→β) = β and by assuming that ''sem''(λ,μ) = λʘμ. This rule says that


- '''from'''  Small(1)  '''and'''  Small(1)→ Small(2) by MP '''we may state''' Small(2);
: - if we are able to prove α at degree λ
   
: - and α β at degree μ
- '''from'''  Small(2)  '''and'''  Small(2)Small(3) by MP '''we may state''' Small(3),
: - then we can prove β at degree λʘμ.




- '''from''' Small(''<u>n-1</u>'')  '''and'''  Small(''<u>n-1</u>'')→ Small(''<u>n</u>'') by MP '''we may state''' Small(''<u>n</u>'').
'''Definition'''. A ''proof'' π of a formula α is a
sequence α<sub>1</sub>,...,α<sub>''m''</sub> of formulas such that α<sub>''m''</sub> = α,
together with a sequence of related ''justifications''. This means that, for every formula α<sub>''i''</sub>, we have to specify whether


:''i'') α<sub>''i''</sub> is assumed as a logical axiom or;
:''ii'') α<sub>''i''</sub> is assumed as an hypothesis or;
:''iii'') α<sub>''i''</sub> is obtained by a rule (in this case we have to indicate the rule and the formulas from α<sub>1</sub>,...,α<sub>''i''-1</sub> used to obtain α<sub>''i''</sub>).


Obviously, a conclusion like Small(20.000) is contrary to our intuition in spite of the fact that the reasoning is correct and the premises appear very reasonable. Clearly, the core of such a paradox lies in the vagueness of the predicate " small" and therefore, as proposed by Goguen (1968/69), we can refer to the notion of approximate reasoning to face it. Indeed it is a fact that everyone is convinced that the implications Small(''<u>n</u>'') → Small(''<u>n+1</u>'') are very close to the truth but not completely true, in general. We can try to "respect" this conviction by assigning to these formulas a truth value λ very close to 1 but different from 1. Then, for example, we can express the hypothesis of the heap paradox by the following fuzzy theory
The justifications are necessary to valuate the proofs. Indeed, let ''s'' be the fuzzy subset of proper axioms and, for every ''i ≤ m'' denote by π(''i'') the proof α<sub>1</sub>,...,α<sub>''i''</sub>. Then the information furnished by π given ''s'' is the value ''Val''(π,''s'') is defined by induction on ''m'' by setting


:''Val''(π, ''s'') = ''la''(α<sub>''m''</sub>) if α<sub>''m''</sub> is assumed as a logical axiom
:''Val''(π, ''s'') = ''s''(α<sub>''m''</sub>) if α<sub>''m''</sub> is assumed as an hypothesis
:''Val''(π,''s'') = ''sem''(''Val''(π(i<sub>1</sub>),''s''),...,''Val''(π(''i''<sub>''n''</sub>),''s''))  if there is a fuzzy rule (''syn'',''sem'') such that α<sub>''m''</sub> = ''syn''(α<sub>''i''<sub>1</sub></sub>,...,α<sub>''i''<sub>''n''</sub></sub>) with ''i''<sub>1</sub> < ''m'',...,''i''<sub>''n''</sub> < ''m''.


Small(1) [to degree 1] 
Now, unlike the usual deduction systems, in a fuzzy deduction system, different proofs of a same formula α may give different pieces of information on the truth degree of α. Then, we have to ''"fuse"'' all these informations.


Small(2) [to degree 1] 
'''Definition'''. The ''deduction operator'' is the operator ''D'' defined by setting
:''D''(''s'')(α)= ''Sup''{''Val''(π,''s'')| π is a proof of α}.
A fuzzy logic is ''axiomatizable'' if there is a fuzzy deduction system such that ''Lc = D''.


...
In Novak 2007 one proves the following basic result.


Small(10.000) [to degree 1] 
'''Proposition'''. In the graded approach Łukasiewicz first order logic is axiomatizable.


Small(10.000)→ Small(10.001)  [to degree λ]
Notice also that, under some natural hypotheses, a fuzzy propositional logic is axiomatizable if and only if the logical connectives are interpreted by continuous functions (see Gerla 2001).


Small(10.001)→ Small(10.002)   [to degree λ]
'''Criticisms.''' A criticism for such an approach is that is not sufficiently flexible. As an example let (''D,I'') be a fuzzy model of a fuzzy theory ''s''. It is evident that both the assignments (''D,I'') and ''s'' cannot be considered definitive and precise since both depends on a subjective valuation. Assume that either (''D,I'') or ''s'' is subject to a slightly variation as a consequence of a tuning process, an essential component in all the applications in fuzzy mathematics. Then it is possible that (''D,I'') ceases completely to be a model of ''s''  while it should be natural to expect (''D,I'') is again a model of ''s'' at some degree.


...
== Continuous logic ==
A very important precursor of fuzzy logic is the '' Continuous logic'' proposed by Chang and Keisler since 1966. In their book all the model theoretical notions of classical logic are extended to first order multi-valued logic. As an example, the notions of quotient, direct product, ultraproduct are defined and examined. Recently, an interesting reformulation of continuous logic was proposed to give a basis for a model theory for the various kinds of ''"metric"'' structures arising in functional analysis and probability theory (see for example Ben I. Y. et al. 2008). Such a reformulation is obtained by referring to the interval [0,1] and by interpreting the logical connectives by a class of continuous functions able to define a ''complete'' approximation system. Also one considers models in which a pseudo-metric is defined to interpret the symbol =. One assumes that all the predicates and function symbols are uniformly continuous with respect such a pseudo-metric. As an example, the finitely additive probabilities can be considered models of a continuous logic once we consider a language for Boolean algebras equipped with a vague monadic predicate ''p'' such that the interpretation of ''p''(''x'') is ''"the event x is probable"''.


== Fuzzy logic with no truth-functional semantics ==
Fuzzy logic extends beyond the truth-functional tradiction of multi-valued logic. The following are two examples.


In accordance, the Heap Paradox argument can be restated as follows where we denote by λ<sup>(n)</sup> the ''n''-power of λ with respect to <math>\otimes</math>.
=== Necessity logic ===
Assume that the deduction apparatus of classical first order logic is presented by a suitable set ''la'' of logical axioms, by the MP-rule and the Generalization rule. Then a fuzzy deduction system is obtained by considering as a fuzzy subset of logical axioms the characteristic function of ''la'' and as fuzzy inference rules the fuzzy Modus Ponens and the extension of the Generalization Rule obtained by assuming that if we prove α at degree λ then we obtain <math> \forall</math>xα(x) at the same degree λ. In suh a case it is easy to see that if ''s'' is a fuzzy theory, then


: ''D''(''s'')(α) = 1 i  α is a logically true formula,
:''D''(''s'')(α) = ''Sup''{''s''(α<sub>1</sub>)ʘ ...ʘ''s''(α<sub>''n''</sub>) : α<sub>1</sub>,..., α<sub>''n''</sub> <math>\vdash</math>α}, otherwise.


'''Since''' Small(10.000) [to degree 1]  
By recalling that the existential quantifier is interpreted by the supremum operator, such a formula arises from a multivalued valuation of the (metalogical) claim: ''"α is a consequence of the fuzzy subset ''s'' of axioms provided there are formulas α<sub>1</sub>, ...,α<sub>n</sub> in ''s'' able to prove <math>\alpha </math>"''. In such a case the vagueness originates from ''s'', i.e., from the notion of "hypothesis". Moreover ''s''(α) is not a truth degree but rather a degree of "preference" or "acceptability" for α. For example, let ʘ be the minimum, ''T'' be a system of axioms for set theory such that the choice axiom ''CA'' does not depend on ''T''. Then we can consider the fuzzy subset of axioms ''s'' defined by setting


'''and''' Small(10.000)→ Small(10.001)          [to degree λ]
:''s''(α) = 1  if α є ''T'',
:''s''(α) = 0.8 if α = ''CA'' ,
'''we state''' Small(10.001) [to degree  1<math>\otimes</math>λ = λ<sup>(1)</sup>]
:''s''(α) = 0 otherwise.


'''since''' Small(10.001) [to degree λ] 
A simple calculation shows that:


'''and''' Small(10.001)→ Small(10.002)        [to degree λ]
:''D''(''s'')(α) = 1  if α is a theorem of ''T'',
:''D''(''s'')(α) = 0.8  if we cannot prove α from ''T'' but α is a theorem of ''T + CA'',
:''D''(''s'')(α) = 0 otherwise .


'''we state''' Small(10.002) [to degree λ<math>\otimes</math>λ = λ<sup>(2) </sup>]
Then, despite the fact that no vague predicate is considered in set theory, in the metalanguage we can consider a vague meta-predicate as "is acceptable" and to represent it by a suitable fuzzy subset ''s''.


. . .
=== Similarity logic ===
 
In accordance with the ideas of M. S. Ying (1994) we can extend necessity logic by introducing a similarity relation among the predicates (see also Biacino, Gerla, Ying (2002)). As an example, consider an inference like
'''since''' Small(<u>10.000+''n''-1</u>) [to degree λ<sup>(n-1)</sup>] 
 
'''and''' Small(<u>10.000+''n''-1</u>) → Small(<u>10.000+''n''</u>)  [to degree λ]
 
'''we state''' Small(<u>10.000+''n''</u>)  [to degree λ<sup>(n-1)</sup><math>\otimes</math>λ = λ<sup>(n)</sup>].
 
 
In particular, we can prove Small(10.000+10.000) at degree  λ<sup>(10.000) </sup>. Now, this is not paradoxical. Indeed if <math>\otimes</math> is the Lukasievicz triangular norm, then λ<sup>(n)</sup> = max {nλ-n+1, 0}. As a consequence, we have that λ<sup>(n)</sup> = 0 for every n ≥ 1/(1-λ).  Assume that λ = 1-10<sup>-4</sup> then λ<sup>(10.000)</sup> = 0.
In this way we get a formal representation of heap argument preserving its intuitive content but avoiding its paradoxical character.
 
=== The falsity of the induction principle ===
In classic mathematics the induction principle is expressed by the schema
A(1) → ((<math>\forall</math>n(A(n) → A(n+1)) → <math>\forall</math>nA(n))
where A is a property defined in the set of natural numbers.
The argument on the basis of  heap paradox enables us to show an interesting fact:
 
''"the induction principle is not valid in fuzzy logic, i.e. we cannot extend such a principle to vague properties"''.
 
In fact, assume that such a principle is satisfied at degree μ ≠ 0 and let λ ≠ 1 such that λ <math>\otimes</math> μ ≠ 0. Also, consider a vague predicate A such that A(1) is valid, <math>\forall</math>n(A(n)) is false and <math>\forall</math>n(A(n) → A(n+1)) is true to degree λ (as in the Heap Paradox). Then, by two application of MP we can prove <math>\forall</math>nA(n) to degree λ<math>\otimes</math> μ ≠ 0. This contradicts the fact that <math>\forall</math>nA(n) is false.
 
Notice that in previous solution of the heap paradox the induction principles was avoided by assuming as an hypothesis the infinite set of ground formulas Small(<u>p</u>)→ Small(<u>p+1</u>), p = 1,2,... and not the formula <math>\forall</math>n Small(n)→Small(n+1). From such an infinite set, we cannot prove <math>\forall</math>n Small(n) in spite of the fact that, given any natural number p, we can prove Small(<u>p</u>).
 
=== The Poincaré paradox ===
The so called “paradox” of Poincaré refers to indistinguishability by emphasizing that, in spite of common intuition, this relation is not transitive. In fact, let d<sub>1</sub>,…, d<sub>m</sub> be a sequence of objects such that we are not able to distinguish d<sub>i</sub> from d<sub>i+1</sub> and that, nevertheless, that we have no difficulty in distinguishing d<sub>1</sub> from d<sub>m</sub>. Also, consider a first order language with a predicate symbol E to denote the indistinguishability relation and, for every ''i'' in ''N'', with a constant c<sub>i</sub> to denote d<sub>i</sub>. Then it is natural to consider the theory defined by the following formulas: 
 
E(c<sub>1</sub>,c<sub>2</sub>),…, E(c<sub>i-1</sub>,c<sub>i</sub>),...,
<math>\neg</math>E(c<sub>1</sub>,c<sub>m</sub>), E(x,z)<math>\and</math>E(z,y) <math>\Rightarrow</math>E(x,y).
 
From such a theory, by suitable applications of the <math>\and</math>-introduction rule, particularization and MP, we can prove  E(c<sub>1</sub>,c<sub>m</sub>) and this contradicts the hypothesis  <math>\neg</math>E(c<sub>1</sub>,c<sub>m</sub>). Consider a value λ very close to 1 and such that λ<sup>(m-1)</sup> = 0. Then in fuzzy logic we can formalize Poincaré argument as follows:
 
'''Step 1'''.
 
'''Since''' E(c<sub>1</sub>,c<sub>2</sub>) [at degree λ]
 
'''and''' E(c<sub>2</sub>,c<sub>3</sub>) [at degree λ]
 
'''we can state''' E(c<sub>1</sub>,c<sub>2</sub>)<math>\and</math>E(c<sub>2</sub>,c<sub>3</sub>)          [at degree λ<sup>(2)</sup>].
 
'''Therefore, since'''
    E(c<sub>1</sub>,c<sub>2</sub>)<math>\and</math>E(c<sub>2</sub>,c<sub>3</sub>)<math>\Rightarrow</math> E(c<sub>1</sub>,c<sub>3</sub>)          [at degree 1]
 
'''we can state'''
E(c<sub>1</sub>,c<sub>3</sub>)  [at degree  λ<sup>(2)</sup>].
 
 
'''Step 2.'''
 
'''Since''' E(c<sub>1</sub>,c<sub>3</sub>)  [at degree  λ<sup>(2)</sup>]
 
'''and''' E(c<sub>3</sub>,c<sub>4</sub>)  [at degree  λ]
 
'''we can state'''
E(c<sub>1</sub>,c<sub>3</sub>)<math>\and</math>E(c<sub>3</sub>,c<sub>4</sub>) [at degree λ<sup>(3)</sup>]
 
'''Therefore, since'''
E(c<sub>1</sub>,c<sub>3</sub>)<math>\and</math>E(c<sub>3</sub>,c<sub>4</sub>)<math>\Rightarrow</math> E(c<sub>1</sub>,c<sub>4</sub>)          [at degree 1]
 
'''we can state''' E(c<sub>1</sub>,c<sub>4</sub>)          [at degree λ<sup>(3)</sup>]
 
...
 
'''Step m-2.'''
   
   
'''Since''' E(c<sub>1</sub>, c<sub>m-1</sub>) [at degree λ<sup>(m-2)</sup>]
:'''Since'''     ''x is a thriller''  <math>\Rightarrow</math>   ''x good for me''          +
:'''and'''                    ''b is a detective story''                +
:'''and'''  ''"detective story"'' is synonymous of  ''"thriller"''
:'''then''' ''"b is good for me"''.


'''and''' E(c<sub>m-1</sub>,c<sub>m</sub>)  [at degree  λ]
Now the synonymy is a vague notion we can represent by a suitable similarity in the set ''W'' of English worlds, i.e. a fuzzy relation ''e'' such that


'''we can state''' E(c<sub>1</sub>, c<sub>m-1</sub>)<math>\and</math>E(c<sub>m-1</sub>, c<sub>m</sub>) [at degree λ<sup>(m-1)</sup>]
: (a)  ''e''(''x'',''x'') = 1  (reflexivity),
: (b)  ''e''(''x'',''z'')ʘ''e''(''z'',''y'') ≤ ''e''(''x'',''y'')    (transitivity),
: (c)  ''e''(''x'',''y'') = ''e''(''y'',''x'')                   (symmetry).


'''Therefore, since''' E(c<sub>1</sub>, c<sub>m-1</sub>)<math>\and</math>E(c<sub>m-1</sub>, c<sub>m</sub>)<math>\Rightarrow</math>E(c<sub>1</sub>, c<sub>m</sub>)  [at degree 1]
Also, as it is usual in fuzzy logic, it is natural to admit that the truth degree of the conclusion "b is good for me" depends on the degree of similarity between the predicates "detective story" and "thriller", obviously. The structure of the corresponding fuzzy inference rule is:


'''we can state'''  E(c<sub>1</sub>, c<sub>m</sub>)          [at degree λ<sup>(m-1)</sup>].
:'''If''' α was proven at degree λ,
:'''and''' α’→ β at degree μ,
:'''then''' β is proven at degree λʘμʘ''e''(α,α’).


Thus, such a proof entails that the conclusion E(c<sub>1</sub>,c<sub>m</sub>) is true at least at degree λ<sup>(m-1)</sup> = 0 (no information). This is not paradoxical.
Every inference rule can be extended in a similar way, i.e. by relaxing the precise matching of the identity with the approximate matching of a similarity. These ideas are also on the basis for a similarity-based [[fuzzy logic programming]].


=== The liar paradox ===
== Effectiveness ==
(to be included)


=== Basic Fuzzy Logic ===
A test to analyze the effectiveness in the ungraded approach to fuzzy logic is to refer to the set of tautologies. Now, since two entailment relations are defined, we have to consider two corresponding notions of tautology.
(to be included)


== Fuzzy logic with no semantics ==


=== Necessity logic ===
'''Definition''' Given a standard algebra ([0,1], ʘ, →, 0, 1) a formula α is a ''standard tautology'' if it is satisfied in every fuzzy interpretation in ([0,1], ʘ, →, 0, 1). The formula α is a ''general tautology'' if it is satisfied in every safe ''Varl''(ʘ)-interpretation.
This very simple fuzzy logic is obtained by an obvious fuzzyfication of first order classical logic. Indeed, assume, for example, that the deduction apparatus of classical first order logic is presented by a suitable set ''la'' of logical axioms, by the MP-rule and the Generalization rule and denote by <math> \vdash </math> the related consequence relation. Then a fuzzy deduction system is obtained by considering as fuzzy subset of logical axioms the characteristic function of ''la'' and as fuzzy inference rules the extension of ''MP'' obtained by assuming that <math> \otimes </math> is the minimum operator <math> \wedge </math>. Moreover, an extension of the Generalization rule is obtained by assuming that if we prove  α at degree λ then we obtain <math> \forall</math>xα(x) at the same degree λ.
Assume that ''D'' is the deduction operator of such a fuzzy logic and that ''s'' is a fuzzy theory. Then D(s)(α) = 1 for every logically true formula α and, otherwise,


<math>D(s)( \alpha) = Sup\{s(\alpha_1)\wedge ...\wedge s(\alpha_n) : \alpha_1,..., \alpha_n \vdash \alpha\}</math>.


By recalling that the existential quantifier is interpreted by the supremum operator, such a formula arises from a multivalued valuation of the (metalogical) claim: ''"α is a consequence of the fuzzy subset s of axioms if there are formulas <math>\alpha_1, ...,\alpha_n</math> in s able to prove <math>\alpha </math>"''
In the first case the following negative result holds true.


It is apparent that in such a case the vagueness originates from ''s'', i.e., from the notion of "hypothesis". Moreover <math>s(\alpha) </math> is not a truth degree but rather a degree of "preference" or "acceptability" for <math> \alpha</math>. For example, let ''T'' be a system of axioms for set theory and assume that the choice axiom ''CA'' does not depend on ''T''.  Then we can consider the fuzzy subset of axioms ''s'' defined by setting


s(α) = 1  if α<math>\in </math> T,
'''Theorem.''' In the case of Łukasiewicz and product logic the set of standard tautologies is not recursively enumerable (see B. Scarpellini (1962)).


s(α) = 0.8 if α = CA ,


s(α) = 0 otherwise.
Such a fact gives a further confirm on the impossibility of an axiomatization of the entailment relation <math>\models</math> and it leads to focalize the attention on <math>\models</math><sub>''Varl''(ʘ)</sub>. At this regard one proves the following theorem.


A simple calculation shows that:


D(s)(α) = 1  if α is a theorem of T,
'''Theorem.''' For each continuous t-norm ʘ, the set of general ʘ-tautologies in first order logic is Σ<sub>1</sub>-complete (and therefore recursively enumerable).


D(s)(α) = 0.8  if we cannot prove α from T but α is a theorem of T + CA,
In the case of the graded approach to face the question of the effectiveness we have to refer to the notion of effectiveness for [[fuzzy subset]] theory. A first proposal in such a direction was made by [[E.S. Santos]] by the notions of ''fuzzy [[Turing machine]]''. Successively, in Biacino and Gerla 2006 the following definition was proposed where ''Ü'' denotes the set of rational numbers in [0,1].


D(s)(α) = 0 otherwise .


Fuzziness in this case is not semantical in nature. Indeed, it is evident that the number <math> s(\alpha) </math>  is a degree of acceptability for <math> \alpha </math> and not a truth degree. In this sense, by recalling the Euclidean distinction between axiom and postulate, perhaps it's better to say ''s'' is the fuzzy subset of the accepted postulates. Thus, despite the fact that no vague predicate is considered in set theory, in the metalanguage we can consider a vague predicate as "is acceptable" and to represent it by a suitable fuzzy subset ''s''. Equivalently, we can interpret <math> s(\alpha) </math> as the degree of preference for <math> \alpha </math> since the only reason we assign to CA the degree 0.8 instead of 1 is that we do not like to use CA.
'''Definition''' A fuzzy subset ''s'' : ''S'' <math>\rightarrow</math>[0,1] of a set ''S'' is ''recursively enumerable'' if a recursive map ''h'' : ''S''×''N'' <math>\rightarrow</math>''Ü'' exists such that, for every ''x'' in ''S'', the function ''h''(''x'',''n'') is increasing with respect to ''n'' and ''s''(''x'') = ''lim h''(''x'',''n'').
 
We say that s is ''decidable'' if both s and its complement –s are recursively enumerable.  
=== Similarity logic ===
In accordance with the ideas of M. S. Ying (1994) we can extend necessity logic by introducing a similarity relation among the predicates (see also Biacino, Gerla, Ying (2002)). As an example, consider an inference like
'''Since'''     x is a thriller  <math>\Rightarrow</math>   x good for me          +
 
'''and'''                   b is a detective story                +
 
'''and'''   "detective story" is synonymous of  "thriller"
 
'''then''' "b is good for me".
 
Now the synonymy is a vague notion we can represent by a suitable similarity ''e'' in the set ''W'' of English worlds, i.e. a fuzzy relation e such that
 
(a)  e(x,x) = 1                          (reflexivity), (b)  e(x,z)<math>\otimes</math>  e(z,y) ≤ e(x,y)    (transitivity), (c)  e(x,y) = e(y,x)                  (symmetry).


Also, as it is usual in fuzzy logic, it is natural to admit that the truth degree of the conclusion "b is good for me" depends on the degree of similarity between the predicates "detective story" and "thriller", obviously. The structure of the corresponding fuzzy inference rule is:


'''If''' α  was proven at degree λ
An extension of such a theory to the general case of the L-subsets is proposed in Gerla (2006) where one refers to the theory of effective domains. It is an open question to give supports for a ''Church thesis'' for fuzzy set theory claiming that the proposed notion of recursive enumerability for fuzzy subsets is the adequate one.


'''and''' α’→ β at degree μ
In Gerla (2001) one proves the following theorem where we refer to fuzzy logics whose deduction apparatus satisfies some obvious effectiveness properties.


'''then''' β is proven at degree λ<math>\otimes</math>μ<math>\otimes</math>e(α,α’).


Every inference rule can be extended in a similar way, i.e. by relaxing the precise matching of the identity with the approximate matching of a similarity. These ideas are also on the basis for a similarity-based [[fuzzy logic programming]].
'''Theorem.''' Given an axiomatizable fuzzy logic, its fuzzy subset ''D''(Ø) of tautologies is recursively enumerable. In particular the fuzzy subset of tautologies in Łukasievicz logic is recursively enumerable in spite of the non recursive enumerability of its cut {α : ''D''(Ø)(α) = 1}.


== Effectiveness ==
=== Effectiveness in the U-approach ===
Denote by ''Lt'' the set of logically true formulas, then it is possible to prove that among the usual first order logics only Gödel logic has a recursively enumerable set of valid formulas. In the case of Lukasiewicz and product logic, for example, ''Lt'' is not recursively enumerable (see B. Scarpellini (1962)). Such a fact was extensively examined in the book of Hájek. Neverthless, from these results we cannot conclude that these logics are not effective and therefore that an axiomatization is not possible. Indeed, there are two possible answers to this criticism. The first one is suggested by the distinction between tautologies and general tautologies in accordance with Hájek’s ideas. We refer to the class of standard algebras, i.e. valuation structures whose domain is [0,1] and whose operations coincide with a given continuous t-norm <math>\otimes</math> together with the related residuum <math>\rightarrow</math>. The following definition works well both for propositional and first order calculus.
'''Definition.''' Given a standard algebra ([0,1], <math>\otimes</math>, <math>\rightarrow</math>), a ''standard  <math>\otimes</math>–tautology'' is a formula assuming the truth value 1 for every interpretation in ([0,1], <math>\otimes</math>, <math>\rightarrow</math>). A ''general <math>\otimes</math>-tautology'' is a formula assuming the truth value 1 for every interpretation in a valuation structure belonging to the variety generated by ([0,1], <math>\otimes</math>, <math>\rightarrow</math>).
Then the general tautologies of the main fuzzy logics refer to the MV-algebras (Lukasiewicz logic), Gödel algebras (Gödel logic), product algebras (product logic) and so on.
'''Theorem.''' For each continuous t-norm <math>\otimes</math>, the set of general <math>\otimes</math>-tautologies in first order logic is Σ<sub>1</sub>-complete (and therefore recursively enumerable).
=== Effectiveness in the G-approach ===
A different answer is necessary if we will consider Pavelka’s approach to fuzzy logic.
Indeed, in such a case the attention is focused on the deduction operator which associates every fuzzy subset of axioms (the available information) with the fuzzy subset of fuzzy theorems. Then, we have to refer to a suitable notion of effectiveness for fuzzy sets. A first proposal in such a direction was made by [[E.S. Santos]] by the notions of ''fuzzy [[Turing machine]]'', ''Markov normal fuzzy algorithm'' and ''fuzzy program''. Successively, [[L. Biacino]] and [[G. Gerla]] proposed the following definition where ''Ü'' denotes the set of rational numbers in [0,1].
'''Definition''' A fuzzy subset s : ''S'' <math>\rightarrow</math>[0,1] of a set ''S'' is ''recursively enumerable'' if a recursive map ''h'' : ''S''×''N'' <math>\rightarrow</math>''Ü'' exists such that, for every ''x'' in ''S'', the function ''h''(''x'',''n'') is increasing with respect to ''n'' and s(''x'') = lim ''h''(''x'',''n'').
We say that s is ''decidable'' if both s and its complement –s are recursively enumerable.
An extension of such a theory to the general case of the L-subsets is proposed in G. Gerla (2006) where one refers to the theory of effective domains.
It is an open question to give supports for a ''Church thesis'' for fuzzy set theory claiming that the proposed notion of recursive enumerability for fuzzy subsets is the adequate one. To this aim, further investigations on the notions of fuzzy grammar and fuzzy Turing machine should be necessary (see for example [[Wiedermann]]'s paper).
In Gerla (2001) one proves the following theorem where we refer to fuzzy logics in which a completeness theorem holds true and whose deduction apparatus satisfies some obvious effectiveness property.
'''Theorem.''' Any axiomatizable fuzzy theory is recursively enumerable. In particular, the fuzzy set of logically true formulas is recursively enumerable in spite of the fact that ''Lt'' is not recursively enumerable, in general. Moreover, any axiomatizable and complete theory is decidable.


It is an open question to use the notion of recursively enumerable fuzzy subset to extend  [[Gödel]]’s limitative theorems to fuzzy logic.
It is an open question to use the notion of recursively enumerable fuzzy subset to extend  [[Gödel]]’s limitative theorems to fuzzy logic.


== Is fuzzy logic a proper extension of classical logic ? ==
==Links==
 
Obviously, the question of the connection between classical and fuzzy logic arises. Now, we can consider this question from two points of views. Firstly, in a fuzzy logics with a truth-functional semantics the interpretation of the logical connectives is ''conservative''. This means that these interpretations coincide with the classical ones in the case we confine ourselves to truth values in {0,1}. So, in such a sense fuzzy logic is a conservative proper extension of classical logic. On the other hand fuzzy logic is defined by using elementary notions of mathematics and therefore it can be reduced to classical logic. From such a point of view, differently from intuitionistic logic, fuzzy logic does not expresses an alternative philosophy. Rather, it is an attempt to express the vagueness phenomena through classical mathematics and therefore through classical logic.


== See also ==
http://www.ggerla.it/
* [[Fuzzy subalgebra]]
* [[Fuzzy associative matrix]]
* [[Fuzzy logic programming]]
* [[Fuzzy set]]
* [[Paradoxes]]
* [[Rough set]]
* [[Similarity logic]]
* [[Necessity logic]]
* [[MV-algebras]]
* [[Basic logic]]


== Bibliography ==
https://en.wikipedia.org/wiki/Fuzzy_logic[[Category:Suggestion Bot Tag]]
* Biacino L., Gerla G., Ying M. S.: Approximate reasoning based on similarity, Math. Log. Quart., 46 (2000), 77-86.
* Chang C. C.,Keisler H. J., ''Continuous Model Theory'', Princeton University Press, Princeton, 1996.
* Cignoli R., D’Ottaviano I. M. L. , Mundici D. , ''Algebraic Foundations of Many-Valued Reasoning''. Kluwer, Dordrecht, 1999.
* Elkan C.. ''The Paradoxical Success of Fuzzy Logic''. November 1993. Available from [http://www.cse.ucsd.edu/users/elkan/ Elkan's home page].
* Hájek P., ''Metamathematics of fuzzy logic''. Kluwer 1998.
* Hájek P., Fuzzy logic and arithmetical hierarchy, ''Fuzzy Sets and Systems'', 3, (1995), 359-363.
* Hájek P., Arithmetical complexity of fuzzy predicate logics – a survey, ''Soft Computing'', 9(2005) 935-941.
* Hájek P., Novák V., The sorites paradox and fuzzy logic, ''Internat. J. General Systems'', 32 (2003) 373-383.
* Klir G. and Folger T., ''Fuzzy Sets, Uncertainty, and Information'' (1988), ISBN 0-13-345984-5.
* Klir G. and Bo Yuan, ''Fuzzy Sets and Fuzzy Logic'' (1995) ISBN 0-13-101171-5
* Gerla G., Fuzzy logic: Mathematical Tools for Approximate Reasoning, Kluwer 2001 ISBN 0-7923-6941-6.
* Gerla G., Effectiveness and Multivalued Logics, ''Journal of Symbolic Logic'', 71 (2006) 137-162.
* Gottwald S., A treatase on Multi-Valued Logics, Research Studies Press LTD, Baldock 2001.
* Goguen J. A., The logic of inexact concepts, ''Synthese'', 19 (1968/69) 325-373.
* Gottwald S., ''A Treatise on Many-Valued Logics, Studies in Logic and Computation'', Research Studies Press, Baldock, 2001.
* Gottwald S., Mathematical fuzzy logic as a tool for the treatment of vague information, ''Information Sciences'', 72, (2005) 41-1.
* Montagna F., Three complexity problems in quantified fuzzy logic. ''Studia Logica'', 68(2001) 143-152.
* Montagna F., On the predicate logic of continuous t-norm BL-algebras, ''Archive for Math. Logic'', 44 (2005) 97-114.
* Novák V., Perfilieva I, Mockor J., ''Mathematical Principles of Fuzzy Logic'', Kluwer Academic Publishers, Dordrecht, (1999).
* Novák V., Fuzzy logic with countable evaluated syntax revisited, Fuzzy Sets and Systems, 158 (2007) 929-936.
* Santos E. S., Fuzzy algorithms, ''Inform. and Control'', 17,(1970), 326-339.
* Pavelka, On fuzzy logic, I-III, ''Zeitschr. Math. Logik Grundl. Math.'', 25, (1979), 45-52, 119-134, 447-464.
* Scarpellini B., Die Nichaxiomatisierbarkeit des unendlichwertigen Prädikatenkalküls von Łukasiewicz, ''J. of Symbolic Logic'', 27,(1962), 159-170.
* Wiedermann J. , Characterizing the super-Turing computing power and efficiency of classical fuzzy Turing machines, ''Theor. Comput. Sci.'' 317, (2004), 61-69.
* Ying M. S., A logic for approximate reasoning, ''J. Symbolic Logic'', 59 (1994).
* Zadeh L. A., Fuzzy Sets, ''Information and Control'', 8 (1965) 338­-353.
* Zadeh L. A., Fuzzy algorithms, ''Information and Control'', 5,(1968), 94-102.
* Zimmermann H., ''Fuzzy Set Theory and its Applications'' (2001), ISBN 0-7923-7435-5.

Latest revision as of 17:01, 17 August 2024

This article is developing and not approved.
Main Article
Discussion
Related Articles  [?]
Bibliography  [?]
External Links  [?]
Citable Version  [?]
 
This editable Main Article is under development and subject to a disclaimer.

Fuzzy logic is a relatively new chapter of formal logic whose aim is to formalize the reasonings involving predicates that are vague in nature (as an example small, near, similar). An example of such kind of reasoning is

If a tomato is red, then the tomato is ripe. Since this tomato is very red, this tomato is very ripe.

Further examples of reasonings involving vague predicates are in the item Paradoxes and fuzzy logic and in the section Fuzzy logic with no truth-functional semantics. The main tool for fuzzy logic is the notion of a fuzzy subset, since a vague predicate is interpreted by a fuzzy subset. Notice that in literature the name "fuzzy logic" also denotes a large series of topics based on an informal usage of the notion of a fuzzy subset, and which are usually devoted to applications.

As a matter of fact, fuzzy logic is an evolution and an enlargement of multi-valued logic since all the definitions and results in the literature on multi-valued logic are also considered in fuzzy logic. In particular, as in multi-valued logic, the starting point is a fixed valuation structure, i.e. a bounded lattice L equipped with suitable operations to interpret the logical connectives. The minimum 0 means 'False', the maximum 1 means 'True', the remaining elements are interpreted as intermediate truth values. The following is the main class of valuation structures (see Hájek 1998, Novák et al. 1999 and Gottwald 2005) corresponding to the connectives and .


Definition. A standard algebra is an algebraic structure ([0,1], ʘ, →, 0,1) where ʘ is a continuous triangular norm, i.e. a continuous, associative, commutative, order preserving operation such that xʘ1 = 1 and → is the related residuation, i.e. xy = sup{z | xʘzy}.


The main examples of standard algebras are obtained by assuming that ʘ is the minimum (Zadeh logic), the usual product (product logic) or that xʘy = Max{x+y-1,0} (Łukasievicz logic). In addition, several authors consider also languages with logical constants to denote rational truth values. Once a valuation structure is fixed, the semantics of the corresponding propositional calculus is defined in a truth-functional way as usual. In first order fuzzy logic the semantics is defined as follows.


Definition. A fuzzy interpretation of a first order language is a pair (D,I) such that D is a nonempty set and I a map associating (as in the classical case) every n-ary operation name h with an n-ary operation in D and every constant c with an element I(c) in D. Moreover, I associates every n-ary predicate name r with an n-ary L-relation I(r) : Dn L in D.


Then the only difference with classical logic is that the interpretation of an n-ary predicate symbol is an n-ary fuzzy relation in D. This enables us to represent properties which are "vague" in nature. Given a fuzzy interpretation we can evaluate the formulas as follows where, given a term t whose variables are in x1,...,xn, we denote by the corresponding n-ary function we define as in classical logic.


Definition. Let (D,I) be a fuzzy interpretation, α a formula whose free variables are in x1,...,xn and d1,...,dn elements in D. Then we define the truth degree Val(I,α,d1,...,dn) by induction as follows :

Val(I, r(t1,...,tp), d1,...,dn) = I(r)(I(t1)(d1,...,dn), ..., I(tp)(d1,...,dn))
Val(I β, d1,...,dn) = Val(I,α,d1,...,dnVal(I,β,d1,...,dn)
Val(I,α → β, d1,...,dn) = Val(I,α, d1,...,dn) → Val(I,β,d1,...,dn)
Val(I, xiα, d1,...,dn) = Inf dєDVal(I,α,d1,...,di-1,d,di+1,...,dn).

In the case there is a propositional constant c* corresponding to a truth value c, we set

Val(I, c*,d1,...,dn) = c.

Observe that in the case L is not complete it is possible that a quantified formula cannot be evaluated. We call safe an interpretation such that all the formulas are evaluated. As usual, if α is a closed formula, then its valuation does not depend on the elements d1,...,dn and we write Val(I,α) instead of Val(I,α,d1,...,dn). More in general, given any formula α, we denote by Val(I, α) the valuation of the universal closure of α.

Two approaches

There are two basic approaches to fuzzy logic. The first one, proposed by P. Hajek and followed by Di Nola, Esteva, Gottwald, Godo, Montagna, Mundici and by a large series of students, is very close to the tradition of multi-valued logic. Indeed the deduction apparatus works on a set of hypotheses to give the corresponding set of logical consequences. This is obtained, as it is usual in multi-valued logic, once a set of designed truth values is fixed. We call, ungraded approach such a way to face fuzzy logic. Another approach was proposed by J. A. Goguen, J. Pavelka, V. Novak, G. Gerla and further authors and it is rather out of line with the tradition of multi-valued logic. Indeed, the deduction apparatus works on a given fuzzy subset of hypotheses (the available information) to give the related fuzzy subset of logical consequences. We call graded approach such a way to face fuzzy logic.

The ungraded approach

In the ungraded approach a subset Des of [0,1] is fixed whose elements are called designed truth degrees. The interpretation is that in Des there are the truth degrees which one considers sufficient to claim the validity of a formula. Usually one sets Des = {1}.


Definition. Let ([0,1], ʘ, →, 0, 1) be a fixed standard algebra, and α be a formula. Then we say that a fuzzy interpretation (D,I) satisfies α provided that Val(I,α) is a designed value. Let T be a theory, then (D,I) is a model of T if every formula in T is satisfied in (D,I). We write T ʘ α if every model of T satisfies α.

The deduction apparatus in the ungraded approach is defined by adopting the same paradigm of classical logic, i.e. a deduction relation is defined by a suitable set of logical axioms and suitable inference rules. The fuzzy logic defined by ʘ is axiomatizable provided that a deduction apparatus exists such that coincides with ʘ. Unfortunately, the main fuzzy logics are not axiomatizable.


Theorem. In all the main fuzzy logics (in particular in Łukasievicz logic) the entailment relation ʘ is not compact. This entails that these logics are not axiomatizable.


As an attempt to bypass such an obstacle, in the ungraded approach one proposes a different entailment relation related with the variety generated by a given triangular norm.


Definition. Given a standard algebra ([0,1], ʘ, →,0,1), denote by Varl(ʘ) the class of all linearly ordered algebras in the variety generated by ([0,1], ʘ, →, 0, 1). Then a Varl(ʘ)-interpretation is an interpretation in a valuation algebra belonging to Varl(ʘ). Given a set T of formulas and a formula α, we write T Varl(ʘ) α provided that every safe Varl(ʘ)-model of T is a safe Varl(ʘ)-model of α.


In such a case, the resulting logic works well. In fact, the following theorem holds true.


Theorem. In all the main fuzzy logics (in particular in Łukasievicz logic) the entailment relation Varl(ʘ) is compact. This is in accordance with the fact that these logics are axiomatizable (provided that they are defined by referring to this relation).


Criticisms. A criticism for the ungraded approach, philosophical in nature, concerns its adequateness to represent the daily reasonings in which vague predicates occur. Moreover the structures in Varl(ʘ) look rather unnatural. For example, in Varl(ʘ) there are structures with infinitesimal truth values. Another criticism is that, while the completeness of [0,1] assures that all the formulas are valuated, in the case we refer to the variety Varl(ʘ), we are forced to admit interpretations for which there are unvaluated formulas.

The graded approach: approximate reasonings

The aim of any logic is to elaborate (uncomplete) information to obtain more explicit information. Now, in the case of fuzzy logic it is natural to admit an information like "the truth values of α is between λ and μ", i.e. a constraint on the possible truth value of a formula. Now, observe that if we admit the usual interpretation of the negation, then Val(I,α)≤ λ if and only if Val(I, α)≥ 1-μ. Then we can reduce all the interval constraints to lower bound constraints. In accordance in the graded approach one proposes the following definition.

Definition . Consider a fuzzy theory s, i.e. a fuzzy subset of formulas. Then a fuzzy interpretation (D,I) is a model of s, in brief (D,I) s if Val(I,α) ≥ s(α). The logical consequence operator is the map Lc : [0,1]F → [0,1]F defined by setting

Lc(s)(α) = Inf{Val(I,α) : (D,I) s}.

Equivalently, we can refer to a graded entailment relation λ by writng s λ α where λ = Inf{Val(I,α) : (D,I) s}.

These definitions are in accordance with the fact that s represents a system of "lower bound constraints" on the unknown truth value of the formulas. Moreover, Lc(s) is the better lower bound constraint we can find given s. In the graded approach we can obtain a deduction apparatus by extending Hilbert's approach as follows.

Definition. A fuzzy inference rule is a pair r = (syn,sem) where syn, the syntactical part, is a partial n-ary operation in F (i.e. an inference rule in the usual sense) and sem, the semantic part, is an n-ary join-preserving operation in [0,1]. An evaluated syntax is a structure (la,R) where la is a fuzzy set of formulas we call fuzzy subset of logical axioms, and R is a set of fuzzy inference rules.

Usually, n = 2 and sem12) is a product like λ1ʘ λ2. As an example, the fuzzy Modus Ponens is defined by assuming that the domain of syn is the set {(α, α→β): α,β are in F}, by setting syn(α, α→β) = β and by assuming that sem(λ,μ) = λʘμ. This rule says that

- if we are able to prove α at degree λ
- and α → β at degree μ
- then we can prove β at degree λʘμ.


Definition. A proof π of a formula α is a sequence α1,...,αm of formulas such that αm = α, together with a sequence of related justifications. This means that, for every formula αi, we have to specify whether

i) αi is assumed as a logical axiom or;
ii) αi is assumed as an hypothesis or;
iii) αi is obtained by a rule (in this case we have to indicate the rule and the formulas from α1,...,αi-1 used to obtain αi).

The justifications are necessary to valuate the proofs. Indeed, let s be the fuzzy subset of proper axioms and, for every i ≤ m denote by π(i) the proof α1,...,αi. Then the information furnished by π given s is the value Val(π,s) is defined by induction on m by setting

Val(π, s) = lam) if αm is assumed as a logical axiom
Val(π, s) = sm) if αm is assumed as an hypothesis
Val(π,s) = sem(Val(π(i1),s),...,Val(π(in),s)) if there is a fuzzy rule (syn,sem) such that αm = syni1,...,αin) with i1 < m,...,in < m.

Now, unlike the usual deduction systems, in a fuzzy deduction system, different proofs of a same formula α may give different pieces of information on the truth degree of α. Then, we have to "fuse" all these informations.

Definition. The deduction operator is the operator D defined by setting

D(s)(α)= Sup{Val(π,s)| π is a proof of α}.

A fuzzy logic is axiomatizable if there is a fuzzy deduction system such that Lc = D.

In Novak 2007 one proves the following basic result.

Proposition. In the graded approach Łukasiewicz first order logic is axiomatizable.

Notice also that, under some natural hypotheses, a fuzzy propositional logic is axiomatizable if and only if the logical connectives are interpreted by continuous functions (see Gerla 2001).

Criticisms. A criticism for such an approach is that is not sufficiently flexible. As an example let (D,I) be a fuzzy model of a fuzzy theory s. It is evident that both the assignments (D,I) and s cannot be considered definitive and precise since both depends on a subjective valuation. Assume that either (D,I) or s is subject to a slightly variation as a consequence of a tuning process, an essential component in all the applications in fuzzy mathematics. Then it is possible that (D,I) ceases completely to be a model of s while it should be natural to expect (D,I) is again a model of s at some degree.

Continuous logic

A very important precursor of fuzzy logic is the Continuous logic proposed by Chang and Keisler since 1966. In their book all the model theoretical notions of classical logic are extended to first order multi-valued logic. As an example, the notions of quotient, direct product, ultraproduct are defined and examined. Recently, an interesting reformulation of continuous logic was proposed to give a basis for a model theory for the various kinds of "metric" structures arising in functional analysis and probability theory (see for example Ben I. Y. et al. 2008). Such a reformulation is obtained by referring to the interval [0,1] and by interpreting the logical connectives by a class of continuous functions able to define a complete approximation system. Also one considers models in which a pseudo-metric is defined to interpret the symbol =. One assumes that all the predicates and function symbols are uniformly continuous with respect such a pseudo-metric. As an example, the finitely additive probabilities can be considered models of a continuous logic once we consider a language for Boolean algebras equipped with a vague monadic predicate p such that the interpretation of p(x) is "the event x is probable".

Fuzzy logic with no truth-functional semantics

Fuzzy logic extends beyond the truth-functional tradiction of multi-valued logic. The following are two examples.

Necessity logic

Assume that the deduction apparatus of classical first order logic is presented by a suitable set la of logical axioms, by the MP-rule and the Generalization rule. Then a fuzzy deduction system is obtained by considering as a fuzzy subset of logical axioms the characteristic function of la and as fuzzy inference rules the fuzzy Modus Ponens and the extension of the Generalization Rule obtained by assuming that if we prove α at degree λ then we obtain xα(x) at the same degree λ. In suh a case it is easy to see that if s is a fuzzy theory, then

D(s)(α) = 1 i α is a logically true formula,
D(s)(α) = Sup{s1)ʘ ...ʘsn) : α1,..., αn α}, otherwise.

By recalling that the existential quantifier is interpreted by the supremum operator, such a formula arises from a multivalued valuation of the (metalogical) claim: "α is a consequence of the fuzzy subset s of axioms provided there are formulas α1, ...,αn in s able to prove ". In such a case the vagueness originates from s, i.e., from the notion of "hypothesis". Moreover s(α) is not a truth degree but rather a degree of "preference" or "acceptability" for α. For example, let ʘ be the minimum, T be a system of axioms for set theory such that the choice axiom CA does not depend on T. Then we can consider the fuzzy subset of axioms s defined by setting

s(α) = 1 if α є T,
s(α) = 0.8 if α = CA ,
s(α) = 0 otherwise.

A simple calculation shows that:

D(s)(α) = 1 if α is a theorem of T,
D(s)(α) = 0.8 if we cannot prove α from T but α is a theorem of T + CA,
D(s)(α) = 0 otherwise .

Then, despite the fact that no vague predicate is considered in set theory, in the metalanguage we can consider a vague meta-predicate as "is acceptable" and to represent it by a suitable fuzzy subset s.

Similarity logic

In accordance with the ideas of M. S. Ying (1994) we can extend necessity logic by introducing a similarity relation among the predicates (see also Biacino, Gerla, Ying (2002)). As an example, consider an inference like

Since x is a thriller x good for me +
and b is a detective story +
and "detective story" is synonymous of "thriller"
then "b is good for me".

Now the synonymy is a vague notion we can represent by a suitable similarity in the set W of English worlds, i.e. a fuzzy relation e such that

(a) e(x,x) = 1 (reflexivity),
(b) e(x,ze(z,y) ≤ e(x,y) (transitivity),
(c) e(x,y) = e(y,x) (symmetry).

Also, as it is usual in fuzzy logic, it is natural to admit that the truth degree of the conclusion "b is good for me" depends on the degree of similarity between the predicates "detective story" and "thriller", obviously. The structure of the corresponding fuzzy inference rule is:

If α was proven at degree λ,
and α’→ β at degree μ,
then β is proven at degree λʘμʘe(α,α’).

Every inference rule can be extended in a similar way, i.e. by relaxing the precise matching of the identity with the approximate matching of a similarity. These ideas are also on the basis for a similarity-based fuzzy logic programming.

Effectiveness

A test to analyze the effectiveness in the ungraded approach to fuzzy logic is to refer to the set of tautologies. Now, since two entailment relations are defined, we have to consider two corresponding notions of tautology.


Definition Given a standard algebra ([0,1], ʘ, →, 0, 1) a formula α is a standard tautology if it is satisfied in every fuzzy interpretation in ([0,1], ʘ, →, 0, 1). The formula α is a general tautology if it is satisfied in every safe Varl(ʘ)-interpretation.


In the first case the following negative result holds true.


Theorem. In the case of Łukasiewicz and product logic the set of standard tautologies is not recursively enumerable (see B. Scarpellini (1962)).


Such a fact gives a further confirm on the impossibility of an axiomatization of the entailment relation and it leads to focalize the attention on Varl(ʘ). At this regard one proves the following theorem.


Theorem. For each continuous t-norm ʘ, the set of general ʘ-tautologies in first order logic is Σ1-complete (and therefore recursively enumerable).

In the case of the graded approach to face the question of the effectiveness we have to refer to the notion of effectiveness for fuzzy subset theory. A first proposal in such a direction was made by E.S. Santos by the notions of fuzzy Turing machine. Successively, in Biacino and Gerla 2006 the following definition was proposed where Ü denotes the set of rational numbers in [0,1].


Definition A fuzzy subset s : S [0,1] of a set S is recursively enumerable if a recursive map h : S×N Ü exists such that, for every x in S, the function h(x,n) is increasing with respect to n and s(x) = lim h(x,n). We say that s is decidable if both s and its complement –s are recursively enumerable.


An extension of such a theory to the general case of the L-subsets is proposed in Gerla (2006) where one refers to the theory of effective domains. It is an open question to give supports for a Church thesis for fuzzy set theory claiming that the proposed notion of recursive enumerability for fuzzy subsets is the adequate one.

In Gerla (2001) one proves the following theorem where we refer to fuzzy logics whose deduction apparatus satisfies some obvious effectiveness properties.


Theorem. Given an axiomatizable fuzzy logic, its fuzzy subset D(Ø) of tautologies is recursively enumerable. In particular the fuzzy subset of tautologies in Łukasievicz logic is recursively enumerable in spite of the non recursive enumerability of its cut {α : D(Ø)(α) = 1}.


It is an open question to use the notion of recursively enumerable fuzzy subset to extend Gödel’s limitative theorems to fuzzy logic.

Links

http://www.ggerla.it/

https://en.wikipedia.org/wiki/Fuzzy_logic