Search Results for author:
Found 3 papers, 0 papers with code
Spectral complexity of deep neural networks
In this paper, we propose to use the angular power spectrum of the limiting field to characterize the complexity of the network architecture.
Quantitative CLTs in Deep Neural Networks
We study the distribution of a fully connected neural network with random Gaussian weights and biases in which the hidden layer widths are proportional to a large constant $n$.
A Quantitative Functional Central Limit Theorem for Shallow Neural Networks
We prove a Quantitative Functional Central Limit Theorem for one-hidden-layer neural networks with generic activation function.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
