Information Plane Analysis Visualization in Deep Learning via Transfer Entropy

arXiv:2404.01364v1 Announce Type: new
Abstract: In a feedforward network, Transfer Entropy (TE) can be used to measure the influence that one layer has on another by quantifying the information transfer between them during training. According to the Information Bottleneck principle, a neural model's internal representation should compress the input data as much as possible while still retaining sufficient information about the output. Information Plane analysis is a visualization technique used to understand the trade-off between compression and information preservation in …

abstract analysis arxiv cs.ai cs.hc cs.it cs.lg data deep learning entropy influence information layer math.it network plane representation the information them training transfer type via visualization