Bridging Logic and Learning: A Neural-Symbolic Approach for Enhanced Reasoning in Neural Models (ASPER)

TL;DR

This paper presents a neural-symbolic approach that combines neural networks with Answer Set Programming to improve reasoning in models, demonstrated by a Sudoku solver trained with minimal data and enhanced reasoning capabilities.

Contribution

Introduces a neural-symbolic method integrating ASP and domain expertise to improve reasoning, with a novel loss function and minimal training data requirements.

Findings

Significant performance improvement in Sudoku solving with only 12 training puzzles.

Effective integration of ASP outputs into neural network training.

Potential applicability to various reasoning domains.

Abstract

Neural-symbolic learning, an intersection of neural networks and symbolic reasoning, aims to blend neural networks' learning capabilities with symbolic AI's interpretability and reasoning. This paper introduces an approach designed to improve the performance of neural models in learning reasoning tasks. It achieves this by integrating Answer Set Programming (ASP) solvers and domain-specific expertise, which is an approach that diverges from traditional complex neural-symbolic models. In this paper, a shallow artificial neural network (ANN) is specifically trained to solve Sudoku puzzles with minimal training data. The model has a unique loss function that integrates losses calculated using the ASP solver outputs, effectively enhancing its training efficiency. Most notably, the model shows a significant improvement in solving Sudoku puzzles using only 12 puzzles for training and testing without hyperparameter tuning. This advancement indicates that the model's enhanced reasoning capabilities have practical applications, extending well beyond Sudoku puzzles to potentially include a variety of other domains. The code can be found on GitHub: https://github.com/Fadi2200/ASPEN.