AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Estimating Information Flow in Deep Neural Networks

Ziv Goldfeld, Ewout Van Den Berg, Kristjan Greenewald, Igor Melnyk, Nam Nguyen, Brian Kingsbury, Yury Polyanskiy

ICML 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 19 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Increase additive-noise variance from β=0.005 to a higher-variance settingSZT model · SZTmutual information compressionHurt
Use ReLU instead of tanhSZT model · SZTmutual information compressionHurt
Add orthonormal weight regularization to the ReLU network (ablation)SZT model · SZTmutual information compressionHurt
Use a deterministic network and vary the bin size used for MI estimationSZT model · SZTestimated mutual informationMixed
Cluster inputs using a non-saturating Leaky-ReLU networkTwo-neuron Leaky-ReLU network · Synthetic two-class examplemutual informationMixed
Use ReLU without weight normalization (ablation)SZT model · SZTmutual information compressionHurt
Use ReLU with orthonormal weight regularization (ablation)SZT model · SZTmutual information compressionHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy