• Skip to main content
  • Skip to primary sidebar

Dharmendra S. Modha

My Work and Thoughts.

  • Brain-inspired Computing
    • Collaborations
    • Videos
  • Life & Universe
    • Creativity
    • Leadership
    • Interesting People
  • Accomplishments
    • Prizes
    • Papers
    • Positions
    • Presentations
    • Press
    • Profiles
  • About Me

PREPRINT: Deep neural networks are robust to weight binarization and other non-linear distortions

June 8, 2016 By dmodha

Guest Blog by Paul A. Merolla

To seek feedback from fellow scientists, my colleagues and I are very excited to share a preprint with the community.

Title: Deep neural networks are robust to weight binarization and other non-linear distortions

Authors: Paul A. Merolla, Rathinakumar Appuswamy, John V. Arthur, Steve K. Esser, Dharmendra S. Modha 

Abstract: Recent results show that deep neural networks achieve excellent performance even when, during training, weights are quantized and projected to a binary representation. Here, we show that this is just the tip of the iceberg: these same networks, during testing, also exhibit a remarkable robustness to distortions beyond quantization, including additive and multiplicative noise, and a class of non-linear projections where binarization is just a special case. To quantify this robustness, we show that one such network achieves 11% test error on CIFAR-10 even with 0.68 effective bits per weight. Furthermore, we find that a common training heuristic–namely, projecting quantized weights during backpropagation–can be altered (or even removed) and networks still achieve a base level of robustness during testing. Specifically, training with weight projections other than quantization also works, as does simply clipping the weights, both of which have never been reported before. We confirm our results for CIFAR-10 and ImageNet datasets. Finally, drawing from these ideas, we propose a stochastic projection rule that leads to a new state of the art network with 7.64% test error on CIFAR-10 using no data augmentation.

Link: http://arxiv.org/abs/1606.01981

Filed Under: Accomplishments, Brain-inspired Computing, Papers

Primary Sidebar

Recent Posts

  • Computer History Museum Interview
  • EE Times Interview by Sunny Bains
  • SiLQ: Simple Large Language Model Quantization-Aware Training
  • Breakthrough low-latency, high-energy-efficiency LLM inference performance using NorthPole
  • Breakthrough edge AI inference performance using NorthPole in 3U VPX form factor

Archives by Month

  • 2025: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2024: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2023: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2022: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2020: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2019: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2018: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2017: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2016: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2015: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2014: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2013: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2012: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2011: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2010: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2009: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2008: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2007: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 2006: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

Copyright © 2025