Inherent Weight Normalization in Stochastic Neural Networks release_vrodwxzlv5dxxfkwom4uzgne24

by Georgios Detorakis, Sourav Dutta, Abhishek Khanna, Matthew Jerry, Suman Datta, Emre Neftci

Released as a article .

2019  

Abstract

Multiplicative stochasticity such as Dropout improves the robustness and generalizability of deep neural networks. Here, we further demonstrate that always-on multiplicative stochasticity combined with simple threshold neurons are sufficient operations for deep neural networks. We call such models Neural Sampling Machines (NSM). We find that the probability of activation of the NSM exhibits a self-normalizing property that mirrors Weight Normalization, a previously studied mechanism that fulfills many of the features of Batch Normalization in an online fashion. The normalization of activities during training speeds up convergence by preventing internal covariate shift caused by changes in the input distribution. The always-on stochasticity of the NSM confers the following advantages: the network is identical in the inference and learning phases, making the NSM suitable for online learning, it can exploit stochasticity inherent to a physical substrate such as analog non-volatile memories for in-memory computing, and it is suitable for Monte Carlo sampling, while requiring almost exclusively addition and comparison operations. We demonstrate NSMs on standard classification benchmarks (MNIST and CIFAR) and event-based classification benchmarks (N-MNIST and DVS Gestures). Our results show that NSMs perform comparably or better than conventional artificial neural networks with the same architecture.
In text/plain format

Archived Files and Locations

application/pdf  609.6 kB
file_zdrob4b4yfeetn3zfkxbfjnwum
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-10-27
Version   v1
Language   en ?
arXiv  1910.12316v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: e39c3e9a-9be3-435a-8c3d-43dcff3f12dd
API URL: JSON