activity
20162026
most citedBinarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

2.2k citations · 5.3k across the 18 of their papers we have counts for

collaborators
Showing 2022Show all

1 paper · 1 filter

cs.LG2022★ 2 cited

Minimum Variance Unbiased N:M Sparsity for the Neural Gradients

Brian Chmiel, Itay Hubara, Ron Banner +1

In deep learning, fine-grained N:M sparsity reduces the data footprint and bandwidth of a General Matrix multiply (GEMM) up to x2, and doubles throughput by skipping computation of…