Information Plane Analysis Visualization in Deep Learning via Transfer Entropy

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 the context of the Information Bottleneck method by plotting the amount of information in the input data against the compressed representation. The claim that there is a causal link between information-theoretic compression and generalization, measured by mutual information, is plausible, but results from different studies are conflicting. In contrast to mutual information, TE can capture temporal relationships between variables. To explore such links, in our novel approach we use TE to quantify information transfer between neural layers and perform Information Plane analysis. We obtained encouraging experimental results, opening the possibility for further investigations.

References in corpus (11)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Measuring Information Transfer
• The information bottleneck method
• Granger causality and transfer entropy are equivalent for Gaussian variables
• Opening the Black Box of Deep Neural Networks via Information
• Differentiating information transfer and causal effect
• Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle
• Entropy and mutual information in models of deep neural networks
• Learning in Feedforward Neural Networks Accelerated by Transfer Entropy
• Transfer entropy-based feedback improves performance in artificial neural networks
• Learning in Convolutional Neural Networks Accelerated by Transfer Entropy