Visualizing the Diversity of Representations Learned by Bayesian Neural Networks
원문 초록
Explainable Artificial Intelligence (XAI) aims to make learning machines less opaque, and offers researchers and practitioners various tools to reveal the decision-making strategies of neural networks. In this work, we investigate how XAI methods can be used for exploring and visualizing the diversity of feature representations learned by Bayesian Neural Networks (BNNs). Our goal is to provide a global understanding of BNNs by making their decision-making strategies a) visible and tangible through feature visualizations and b) quantitatively measurable with a distance measure learned by contrastive learning. Our work provides new insights into the \emph{posterior} distribution in terms of human-understandable feature information with regard to the underlying decision making strategies. The main findings of our work are the following: 1) global XAI methods can be applied to explain the diversity of decision-making strategies of BNN instances, 2) Monte Carlo dropout with commonly used Dropout rates exhibit increased diversity in feature representations compared to the multimodal posterior approximation of MultiSWAG, 3) the diversity of learned feature representations highly correlates with the uncertainty estimate for the output and 4) the inter-mode diversity of the multimodal posterior decreases as the network width increases, while the intra mode diversity increases. These findings are consistent with the recent Deep Neural Networks theory, providing additional intuitions about what the theory implies in terms of humanly understandable concepts.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Enhancing Cluster Analysis With Explainable AI and Multidimensional Cluster Prototypes
Communicating Smartly in the Molecular Domain: Neural Networks in the Internet of Bio-Nano Things
Explainable Artificial Intelligence in Biomedical Image Analysis: A Comprehensive Survey
Towards Transparent AI: A Survey on Explainable Large Language Models
Toward the Explainability of Protein Language Models for Sequence Design
Perceptual Rationality: An Evolutionary Game Theory of Perceptually Rational Decision-Making
토론
이 논문과 연결된 포럼 글이 아직 없습니다.