SOTAVerified

Information Plane

To obtain the Information Plane (IP) of deep neural networks, which shows the trajectories of the hidden layers during training in a 2D plane using as coordinate axes the mutual information between the input and the hidden layer, and the mutual information between the output and the hidden layer.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 30 papers

TitleStatusHype
A Provably Convergent Information Bottleneck Solution via ADMMCode0
Information flows of diverse autoencodersCode0
Scalable Mutual Information Estimation using Dependence GraphsCode0
End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise TrainingCode0
Opening the Black Box of Deep Neural Networks via InformationCode0
The Dual Information BottleneckCode0
On the Information Bottleneck Theory of Deep LearningCode0
HRel: Filter Pruning based on High Relevance between Activation Maps and Class LabelsCode0
Malicious Network Traffic Detection via Deep Learning: An Information Theoretic ViewCode0
On the Information Plane of AutoencodersCode0
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.