Next Article in Journal
Non-Invasive Blood Glucose Monitoring Using a Curved Goubau Line
Previous Article in Journal
An Adaptable Train-to-Ground Communication Architecture Based on the 5G Technological Enabler SDN
Previous Article in Special Issue
Jet Features: Hardware-Friendly, Learned Convolutional Kernels for High-Speed Image Classification
Article Menu

Export Article

Open AccessFeature PaperReview

A Review of Binarized Neural Networks

Electrical and Computer Engineering, Brigham Young University, Provo, UT 84602, USA
*
Author to whom correspondence should be addressed.
Electronics 2019, 8(6), 661; https://doi.org/10.3390/electronics8060661
Received: 14 May 2019 / Revised: 3 June 2019 / Accepted: 5 June 2019 / Published: 12 June 2019
  |  
PDF [376 KB, uploaded 12 June 2019]
  |     |  

Abstract

In this work, we review Binarized Neural Networks (BNNs). BNNs are deep neural networks that use binary values for activations and weights, instead of full precision values. With binary values, BNNs can execute computations using bitwise operations, which reduces execution time. Model sizes of BNNs are much smaller than their full precision counterparts. While the accuracy of a BNN model is generally less than full precision models, BNNs have been closing accuracy gap and are becoming more accurate on larger datasets like ImageNet. BNNs are also good candidates for deep learning implementations on FPGAs and ASICs due to their bitwise efficiency. We give a tutorial of the general BNN methodology and review various contributions, implementations and applications of BNNs. View Full-Text
Keywords: Binarized Neural Networks; Deep Neural Networks; deep learning; FPGA; digital design; deep neural network compression Binarized Neural Networks; Deep Neural Networks; deep learning; FPGA; digital design; deep neural network compression
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Simons, T.; Lee, D.-J. A Review of Binarized Neural Networks. Electronics 2019, 8, 661.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Electronics EISSN 2079-9292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top