Deep neural networks with dependent weights: Gaussian process mixture limit, heavy tails, sparsity and compressibility
This article studies the infinite-width limit of deep feedforward neural networks whose weights are dependent, and modelled via a mixture of Gaussian distributions. Each hidden node of the network is assigned a nonnegative random variable that controls the variance of the outgoing weights of that no...
| Hlavní autoři: | , , , , , |
|---|---|
| Médium: | Journal article |
| Jazyk: | English |
| Vydáno: |
Journal of Machine Learning Research
2023
|