Symbolic Knowledge Extraction using Łukasiewicz Logics
This work addresses the challenge of bridging logic-based and neural network approaches for AI researchers, though it appears incremental as it builds on existing Łukasiewicz logic methods.
The paper tackled the problem of integrating symbolic and connectionist AI systems by using finite truth-valued Łukasiewicz logic to inject first-order formulas into neural networks, enabling symbolic rule extraction with reduced plasticity while maintaining learning performance, as demonstrated in reverse engineering truth tables and extracting formulas from real datasets.
This work describes a methodology that combines logic-based systems and connectionist systems. Our approach uses finite truth-valued Łukasiewicz logic, wherein every connective can be defined by a neuron in an artificial network. 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 Łukasiewicz 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.