Physical Rule-Guided Convolutional Neural Network

TL;DR

This paper introduces a Physics-Guided CNN that integrates scientific rules as custom layers, improving performance and interpretability in data-limited scenarios by reducing false positives and boosting confidence scores.

Contribution

It presents a novel architecture that incorporates automated, trainable physics-based rules into CNNs, enhancing their effectiveness in complex, data-scarce environments.

Findings

Superior performance over baseline CNNs on multiple datasets

Significant reduction in false positives

Enhanced confidence scores for true detections

Abstract

The black-box nature of Convolutional Neural Networks (CNNs) and their reliance on large datasets limit their use in complex domains with limited labeled data. Physics-Guided Neural Networks (PGNNs) have emerged to address these limitations by integrating scientific principles and real-world knowledge, enhancing model interpretability and efficiency. This paper proposes a novel Physics-Guided CNN (PGCNN) architecture that incorporates dynamic, trainable, and automated LLM-generated, widely recognized rules integrated into the model as custom layers to address challenges like limited data and low confidence scores. The PGCNN is evaluated on multiple datasets, demonstrating superior performance compared to a baseline CNN model. Key improvements include a significant reduction in false positives and enhanced confidence scores for true detection. The results highlight the potential of PGCNNs to improve CNN performance for broader application areas.