Author:
Carlos Leandro
Affiliation:
Instituto Superior de Engenharia de Lisboa, Portugal
Keyword(s):
Fuzzy logics, Łukasiewicz logic, Reverse Engineering, Symbolic Knowledge Extraction, Neural Networks, Link grammars, Levenderg-Marquardt algorithm, Optimal Brain Surgeon.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Computational Intelligence
;
Fuzzy Information Retrieval and Data Mining
;
Fuzzy Systems
;
Learning and Adaptive Fuzzy Systems
;
Soft Computing
Abstract:
This work describes a methodology that combines logic-based systems and connectionist systems. Our approach uses finite truth-valued Łukasiewicz logic, where we take advantage of fact, presented in (Castro and Trillas, 1998), wherein every connective can be defined by a neuron in an artificial network having, by activation function, the identity truncated to zero and one. This allowed the injection of formulas into a network architecture, and also simplified symbolic rule extraction. Neural networks are trained using the Levenderg-Marquardt algorithm, where we restricted the knowledge dissemination in the network structure, and the generated network is simplified applying the ”Optimal Brain Surgeon” algorithm proposed by B. Hassibi, D.
G. Stork and G.J. Wolf. 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 Łukasiewicz logic languag
e and simplifying the translation between symbolic and connectionist structures. We used this method in the reverse engineering problem of finding the formula used on the generation of a given truth table. For real data sets the method is particularly useful for attribute selection, on binary classification problems defined using nominal attributes, where each instance has a level of uncertainty associated with it.
(More)