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
Information Plane Analysis of Deep Neural Networks via Matrix--Based Renyi's Entropy and Tensor Kernels—0
On Predictive Information Sub-optimality of RNNs—0
On the Trajectory of Stochastic Gradient Descent in the Information Plane—0
REPRESENTATION COMPRESSION AND GENERALIZATION IN DEEP NEURAL NETWORKS—0
Evaluating Capability of Deep Neural Networks for Image Classification via Information Plane—0
Understanding Autoencoders with Information Theoretic Concepts—0
Scalable Mutual Information Estimation using Dependence GraphsCode0
On the Information Bottleneck Theory of Deep LearningCode0
Opening the Black Box of Deep Neural Networks via InformationCode0
Distinguishing noise from chaos: objective versus subjective criteria using Horizontal Visibility Graph—0
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.