Symbolic Knowledge Extraction using Łukasiewicz Logics
نویسنده
چکیده
This work describes a methodology that combines logic-based systems and connectionist systems. Our approach uses finite truth-valued Lukasiewicz logic, wherein every connective can be defined by a neuron in an artificial network [1]. This allowed the injection of first-order formulas into a network architecture, and also simplified symbolic rule extraction. For that we trained a neural networks using the Levenderg-Marquardt algorithm, where we restricted the knowledge dissemination in the network structure. This procedure reduces neural network plasticity without drastically damaging the learning performance, thus making the descriptive power of produced neural networks similar to the descriptive power of Lukasiewicz logic language and simplifying the translation between symbolic and connectionist structures. We used this method for reverse engineering truth table and in extraction of formulas from real data sets. ———————————————————————-
منابع مشابه
Reverse Engineering and Symbolic Knowledge Extraction on Łukasiewicz Fuzzy Logics using Linear Neural Networks
This work describes a methodology to combine logic-based systems and connectionist systems. Our approach uses finite truth valued Lukasiewicz logic, where we take advantage of fact, presented by Castro in [6], what in this type of logics every connective can be define by a neuron in an artificial network having by activation function the identity truncated to zero and one. This allowed the inje...
متن کاملKnowledge Extraction and Knowledge Integration governed by Łukasiewicz Logics
The development of machine learning in particular and artificial intelligent in general has been strongly conditioned by the lack of an appropriate interface layer between deduction, abduction and induction [1]. In this work we extend traditional algebraic specification methods [2] in this direction. Here we assume that such interface for AI emerges from an adequate Neural-Symbolic integration ...
متن کاملOn Qualified Cardinality Restrictions in Fuzzy Description Logics under Łukasiewicz semantics
Fuzzy Description Logics have been proposed as a family of languages to describe vague or imprecise structured knowledge. This work deals with one of the less studied constructors, qualified cardinality restrictions, showing some counter-intuitive behaviours under Łukasiewicz semantics, and proposing a new semantics and the corresponding reasoning algorithm.
متن کاملSyntactic Labelled Tableaux for Lukasiewicz Fuzzy ALC
Fuzzy description logics (DLs) serve as a tool to handle vagueness in real-world knowledge. There is particular interest in logics implementing Łukasiewicz semantics, which has a number of favourable properties. Current decision procedures for Łukasiewicz fuzzy DLs work by reduction to exponentially large mixed integer programming problems. Here, we present a decision method that stays closer t...
متن کاملŁukasiewicz Fuzzy EL is Undecidable
Fuzzy Description Logics have been proposed as formalisms for representing and reasoning about imprecise knowledge by introducing intermediate truth degrees. Unfortunately, it has been shown that reasoning in these logics easily becomes undecidable, when infinitely many truth degrees are considered and conjunction is not idempotent. In this paper, we take those results to the extreme, and show ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1604.03099 شماره
صفحات -
تاریخ انتشار 2016