Neural-Symbolic Integration with Evolvable Policies
Authors:
- Marios ThomaMTMarios Thoma
- Vassilis VassiliadesVVVassilis Vassiliades
Preprint
Abstract
Neural-Symbolic (NeSy) Artificial Intelligence has emerged as a promising approach for combining the learning capabilities of neural networks with the interpretable reasoning of symbolic systems. However, existing NeSy frameworks typically require either predefined symbolic policies or policies that are differentiable, limiting their applicability when domain expertise is unavailable or when policies are inherently non-differentiable. We propose a framework that addresses this limitation by enabling the concurrent learning of both non-differentiable symbolic policies and neural network weights through an evolutionary process. Our approach casts NeSy systems as organisms in a population that evolve through mutations (both symbolic rule additions and neural weight changes), with fitness-based selection guiding convergence toward hidden target policies. The framework extends the NEUROLOG architecture to make symbolic policies trainable, adapts Valiant's Evolvability framework to the NeSy context, and employs Machine Coaching semantics for mutable symbolic representations. Neural networks are trained through abductive reasoning from the symbolic component, eliminating differentiability requirements. Through extensive experimentation, we demonstrate that NeSy systems starting with empty policies and random neural weights can successfully approximate hidden non-differentiable target policies, achieving median correct performance approaching 100%. This work represents a step toward enabling NeSy research in domains where the acquisition of symbolic knowledge from experts is challenging or infeasible.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Solving olympiad geometry without human demonstrationsNature, 2024
- An Experimental Overview of Neural-Symbolic Systems2023
- Cost of Explainability in AI: An Example with Credit Scoring Models2023
- Neurosymbolic AI: the 3rd waveArtificial Intelligence Review, 2023
- Prudens: An Argumentation-Based Language for Cognitive Assistants2022
- EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: The MonuMAI cultural heritage use caseInformation Fusion, 2022
- Quality-Diversity Optimization: A Novel Branch of Stochastic Optimization2021
- Explaining the black-box model: A survey of local interpretation methods for deep neural networksNeurocomputing, 2021
- On probabilistic inference by weighted model countingArtificial Intelligence, 2008
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998