A Novel Neural-symbolic System under Statistical Relational Learning

TL;DR

This paper introduces NSF-SRL, a neural-symbolic framework that combines deep learning with symbolic reasoning to improve AI's generalization, interpretability, and performance across various learning tasks.

Contribution

It presents a novel statistical relational learning-based neural-symbolic system that enhances integration, generalization, and interpretability in AI models.

Findings

Achieves high performance in supervised, weakly supervised, and zero-shot learning.

Provides a quantitative method to evaluate interpretability.

Visualizes logic rules to explain model predictions.

Abstract

A key objective in the field of artificial intelligence is to develop cognitive models that can exhibit human-like intellectual capabilities. One promising approach to achieving this is through neural-symbolic systems, which combine the strengths of deep learning and symbolic reasoning. However, current methodologies in this area face limitations in integration, generalization, and interpretability. To address these challenges, we propose a neural-symbolic framework based on statistical relational learning, referred to as NSF-SRL. This framework effectively integrates deep learning models with symbolic reasoning in a mutually beneficial manner.In NSF-SRL, the results of symbolic reasoning are utilized to refine and correct the predictions made by deep learning models, while deep learning models enhance the efficiency of the symbolic reasoning process. Through extensive experiments, we demonstrate that our approach achieves high performance and exhibits effective generalization in supervised learning, weakly supervised and zero-shot learning tasks. Furthermore, we introduce a quantitative strategy to evaluate the interpretability of the model's predictions, visualizing the corresponding logic rules that contribute to these predictions and providing insights into the reasoning process. We believe that this approach sets a new standard for neural-symbolic systems and will drive future research in the field of general artificial intelligence.