Skip to yearly menu bar Skip to main content


Virtual presentation / poster accept

Information Plane Analysis for Dropout Neural Networks

Linara Adilova · Bernhard C Geiger · Asja Fischer

Keywords: [ mutual information ] [ continuous distributions ] [ information plane ] [ deep learning ] [ dropout ] [ Deep Learning and representational learning ]


Abstract:

The information-theoretic framework promises to explain the predictive power of neural networks. In particular, the information plane analysis, which measures mutual information (MI) between input and representation as well as representation and output, should give rich insights into the training process. This approach, however, was shown to strongly depend on the choice of estimator of the MI. The problem is amplified for deterministic networks if the MI between input and representation is infinite. Thus, the estimated values are defined by the different approaches for estimation, but do not adequately represent the training process from an information-theoretic perspective. In this work, we show that dropout with continuously distributed noise ensures that MI is finite. We demonstrate in a range of experiments that this enables a meaningful information plane analysis for a class of dropout neural networks that is widely used in practice.

Chat is not available.