Skip to yearly menu bar Skip to main content


WWW: A Unified Framework for Explaining What Where and Why of Neural Networks by Interpretation of Neuron Concepts

Yong Hyun Ahn · Hyeon Bae Kim · Seong Tae Kim

Arch 4A-E Poster #128
[ ]
Thu 20 Jun 10:30 a.m. PDT — noon PDT


Recent advancements in neural networks have showcased their remarkable capabilities across various domains. Despite these successes, the “black box” problemstill remains. Addressing this, we propose a novel framework, WWW, that offers the ‘what’, ‘where’, and ‘why’of the neural network decisions in human-understandableterms. Specifically, WWW utilizes adaptive selection forconcept discovery, employing adaptive cosine similarityand thresholding techniques to effectively explain ‘what’.To address the ‘where’ and ‘why’, we proposed a novelcombination of neuron activation maps (NAMs) with Shapleyvalues, generating localized concept maps and heatmapsfor individual inputs. Furthermore, WWW introduces amethod for predicting uncertainty, leveraging heatmap similarities to estimate ‘how’ reliable the prediction is. Experimental evaluations of WWW demonstrate superior performance in both quantitative and qualitative metrics, outperforming existing methods in interpretability. WWW provides a unified solution for explaining ‘what’, ‘where’, and‘why’, introducing a method for localized explanations fromglobal interpretations and offering a plug-and-play solutionadaptable to various architectures.

Live content is unavailable. Log in and register to view live content