Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Simon Wiedemann, Temesgen Mehari, Kevin Kepp, Wojciech Samek. Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR Workshops 2020, Seattle, WA, USA, June 14-19, 2020. pages 3096-3104, IEEE, 2020. [doi]

This author has not been identified. Look up 'Simon Wiedemann' in GoogleThis author has not been identified. Look up 'Temesgen Mehari' in GoogleThis author has not been identified. Look up 'Kevin Kepp' in GoogleThis author has not been identified. Look up 'Wojciech Samek' in Google

runs on WebDSL