Search Results for author:
Found 2 papers, 1 papers with code
On Characterizing the Evolution of Embedding Space of Neural Networks using Algebraic Topology
We study how the topology of feature embedding space changes as it passes through the layers of a well-trained deep neural network (DNN) through Betti numbers.
Altering Backward Pass Gradients improves Convergence
In standard neural network training, the gradients in the backward pass are determined by the forward pass.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
