Neural network interpretability with layer-wise relevance propagation: novel techniques for neuron selection and visualization

TL;DR

This paper introduces a novel layer-wise relevance propagation method that improves neuron selection and visualization in neural networks, enhancing interpretability and transparency in AI systems for computer vision.

Contribution

The paper presents a new approach that refines neuron relevance evaluation during LRP, using graph visualization and heatmaps to better interpret neural network decisions.

Findings

Enhanced interpretability of neural networks through improved neuron relevance parsing.

Visualization techniques like heatmaps and deconvolutional reconstructions provide clearer insights.

Experimental results show increased accuracy in identifying critical neurons.

Abstract

Interpreting complex neural networks is crucial for understanding their decision-making processes, particularly in applications where transparency and accountability are essential. This proposed method addresses this need by focusing on layer-wise Relevance Propagation (LRP), a technique used in explainable artificial intelligence (XAI) to attribute neural network outputs to input features through backpropagated relevance scores. Existing LRP methods often struggle with precision in evaluating individual neuron contributions. To overcome this limitation, we present a novel approach that improves the parsing of selected neurons during LRP backward propagation, using the Visual Geometry Group 16 (VGG16) architecture as a case study. Our method creates neural network graphs to highlight critical paths and visualizes these paths with heatmaps, optimizing neuron selection through accuracy metrics like Mean Squared Error (MSE) and Symmetric Mean Absolute Percentage Error (SMAPE). Additionally, we utilize a deconvolutional visualization technique to reconstruct feature maps, offering a comprehensive view of the network's inner workings. Extensive experiments demonstrate that our approach enhances interpretability and supports the development of more transparent artificial intelligence (AI) systems for computer vision applications. This advancement has the potential to improve the trustworthiness of AI models in real-world machine vision applications, thereby increasing their reliability and effectiveness.