Estimating Information Flow in Deep Neural Networks
Copyright © 2019 ASME We study the estimation of the mutual information I(X;Tℓ) between the input X to a deep neural network (DNN) and the output vector Tℓ of its ℓth hidden layer (an "internal representation"). Focusing on feedforward networks with fixed weights and noisy internal represe...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
2021-11-05T14:29:09Z.
|
| Subjects: | |
| Online Access: | Get fulltext |