On the information bottleneck theory of deep learning
From MaRDI portal
Publication:5854125
DOI10.1088/1742-5468/ab3985zbMath1459.68185OpenAlexW2996320484MaRDI QIDQ5854125
David D. Cox, Artemy Kolchinsky, Joel Dapello, Brendan D. Tracey, Yamini Bansal, Madhu S. Advani, Andrew M. Saxe
Publication date: 16 March 2021
Published in: Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1088/1742-5468/ab3985
Artificial neural networks and deep learning (68T07) Neural networks for/in biological studies, artificial life and related topics (92B20)
Related Items (10)
Understanding Deep Learning with Statistical Relevance ⋮ Relative stability toward diffeomorphisms indicates performance in deep nets* ⋮ Learning when to stop: a mutual information approach to prevent overfitting in profiled side-channel analysis ⋮ Towards interpreting deep neural networks via layer behavior understanding ⋮ The role of mutual information in variational classifiers ⋮ Landscape and training regimes in deep learning ⋮ On the stability and generalization of neural networks with VC dimension and fuzzy feature encoders ⋮ ChaosNet: A chaos based artificial neural network architecture for classification ⋮ Geometric compression of invariant manifolds in neural networks ⋮ Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness
Uses Software
Cites Work
This page was built for publication: On the information bottleneck theory of deep learning
