Web: http://arxiv.org/abs/2201.02711

Jan. 31, 2022, 2:11 a.m. | Hongyi Pan, Diaa Badawi, Ahmet Enis Cetin

cs.LG updates on arXiv.org arxiv.org

Convolution has been the core operation of modern deep neural networks. It is
well-known that convolutions can be implemented in the Fourier Transform
domain. In this paper, we propose to use binary block Walsh-Hadamard transform
(WHT) instead of the Fourier transform. We use WHT-based binary layers to
replace some of the regular convolution layers in deep neural networks. We
utilize both one-dimensional (1-D) and two-dimensional (2-D) binary WHTs in
this paper. In both 1-D and 2-D layers, we compute the …

arxiv deep networks neural neural networks

More from arxiv.org / cs.LG updates on arXiv.org

Data Analytics and Technical support Lead

@ Coupa Software, Inc. | Bogota, Colombia

Data Science Manager

@ Vectra | San Jose, CA

Data Analyst Sr

@ Capco | Brazil - Sao Paulo

Data Scientist (NLP)

@ Builder.ai | London, England, United Kingdom - Remote

Senior Data Analyst

@ BuildZoom | Scottsdale, AZ/ San Francisco, CA/ Remote

Senior Research Scientist, Speech Recognition

@ SoundHound Inc. | Toronto, Canada