arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.10859cs.LGcs.AIcs.CVstat.ML
收藏

可视化贝叶斯神经网络学习到的表征多样性

Visualizing the Diversity of Representations Learned by Bayesian Neural Networks

Machine Learning Group(机器学习研究组);Technical University of Berlin(柏林工业大学);BIFOLD – Berlin Institute for the Foundations of Learning and Data(BIFOLD – 柏林学习与数据基础研究所);Understandable Machine Intelligence Lab(可理解机器智能实验室);Leibniz Institute for Agriculture and Bioeconomy (ATB)(莱布尼茨农业与生物经济研究所(ATB));RIKEN Center for AIP(理化学研究所人工智能创新中心)

Dennis Grinwald, Kirill Bykov, Shinichi Nakajima, Marina M. -C. Höhne

AI总结:

本研究利用可解释AI方法可视化和量化贝叶斯神经网络的表征多样性,发现MC Dropout比MultiSWAG更具多样性,且多样性随网络宽度变化,与深度网络理论一致。

摘要:

可解释人工智能(XAI)旨在使学习机器不那么不透明,并为研究人员和从业者提供各种工具来揭示神经网络的决策策略。在这项工作中,我们研究了如何使用XAI方法来探索和可视化贝叶斯神经网络(BNNs)学习到的特征表征的多样性。我们的目标是通过使BNNs的决策策略a)通过特征可视化可见且可感知,以及b)通过对比学习学到的距离度量进行定量测量,来提供对BNNs的全局理解。我们的工作从人类可理解的特征信息角度,为关于底层决策策略的\emph{后验}分布提供了新的见解。我们工作的主要发现如下:1)全局XAI方法可应用于解释BNN实例决策策略的多样性;2)使用常用Dropout率的蒙特卡洛Dropout在特征表征方面表现出比MultiSWAG的多模态后验近似更大的多样性;3)学习到的特征表征的多样性与输出的不确定性估计高度相关;4)多模态后验的模态间多样性随着网络宽度的增加而减少,而模态内多样性则增加。这些发现与最近的深度神经网络理论一致,为该理论在人类可理解概念方面的含义提供了额外的直觉。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑