Article
A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit - Nature Machine Intelligence
Rating:
0.0
Views:
52
Likes:
1
Library:
1
Despite the practical success of deep neural networks, a comprehensive theoretical framework that can predict practically relevant scores, such as the test accuracy, from knowledge of the training data is currently lacking. Huge simplifications arise in the infinite-width limit, in which the number of units Nℓ in each hidden layer (ℓ = 1, …, L, where L is the depth of the network) far exceeds the number P of training examples.
Rate This Post
Rate The Educational Value
Rate The Ease of Understanding and Presentation
Interesting or Boring? Rate the Entertainment Value