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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ahn, Yong Hyun, Kim, Hyeon Bae, Kim, Seong Tae
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916200681832448
author Ahn, Yong Hyun
Kim, Hyeon Bae
Kim, Seong Tae
author_facet Ahn, Yong Hyun
Kim, Hyeon Bae
Kim, Seong Tae
contents Recent advancements in neural networks have showcased their remarkable capabilities across various domains. Despite these successes, the "black box" problem still remains. Addressing this, we propose a novel framework, WWW, that offers the 'what', 'where', and 'why' of the neural network decisions in human-understandable terms. Specifically, WWW utilizes adaptive selection for concept discovery, employing adaptive cosine similarity and thresholding techniques to effectively explain 'what'. To address the 'where' and 'why', we proposed a novel combination of neuron activation maps (NAMs) with Shapley values, generating localized concept maps and heatmaps for individual inputs. Furthermore, WWW introduces a method 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 from global interpretations and offering a plug-and-play solution adaptable to various architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2402_18956
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle WWW: A Unified Framework for Explaining What, Where and Why of Neural Networks by Interpretation of Neuron Concepts
Ahn, Yong Hyun
Kim, Hyeon Bae
Kim, Seong Tae
Computer Vision and Pattern Recognition
Recent advancements in neural networks have showcased their remarkable capabilities across various domains. Despite these successes, the "black box" problem still remains. Addressing this, we propose a novel framework, WWW, that offers the 'what', 'where', and 'why' of the neural network decisions in human-understandable terms. Specifically, WWW utilizes adaptive selection for concept discovery, employing adaptive cosine similarity and thresholding techniques to effectively explain 'what'. To address the 'where' and 'why', we proposed a novel combination of neuron activation maps (NAMs) with Shapley values, generating localized concept maps and heatmaps for individual inputs. Furthermore, WWW introduces a method 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 from global interpretations and offering a plug-and-play solution adaptable to various architectures.
title WWW: A Unified Framework for Explaining What, Where and Why of Neural Networks by Interpretation of Neuron Concepts
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.18956