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.
Abstract (translated)
卷积神经网络（CNNs）的黑盒性质以及它们对大量数据集的依赖限制了它们在缺乏标注数据且复杂领域的应用。为了克服这些限制，物理引导神经网络（PGNNs）应运而生，通过将科学原理和现实世界知识相结合，提高了模型的可解释性和效率。本文提出了一个新颖的物理引导卷积神经网络（PGCNN）架构，将动态、可训练的和自动生成的LLM（局部逻辑模块）集成到模型中作为自定义层，以解决诸如有限数据和低置信度分数等问题。PGCNN在多个数据集上的评估表明，其性能优于基线CNN模型。关键的改进包括显著的假阳性减少和真实检测的信心分数的增强。结果强调了PGNNs改善 CNN性能并为更广泛的应用领域提供潜力的潜力。
URL
https://arxiv.org/abs/2409.02081
