A comprehensive study on binary optimizer and its applicabilityDownload PDF

Dec 29, 2019 (edited Oct 13, 2020)NeurIPS 2019 Reproducibility Challenge Blind ReportReaders: Everyone
  • Abstract: Binarized Neural Networks are paving a way towards the deployment of deep neural networks with less memory and computation. In this report, we present a detailed study on the paper titled "Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization" which proposes a new optimization method for training BNN called BOP. We first investigate the effect of using latent weights in BNN for analyzing prediction performance in terms of accuracy. Next, a comprehensive ablation study on hyperparameters is provided. Finally, we explore the usability of BNN in denoising autoencoders. Code for all our experiments are available at https://github.com/nancy-nayak/rethinking-bnn/.
  • Track: Ablation
  • NeurIPS Paper Id: https://openreview.net/forum?id=BJe_nNrgIS
3 Replies