Controlling information capacity of binary neural network


METADATA ONLY
Loading...

Date

2020-10

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Despite the growing popularity of deep learning technologies, high memory requirements and power consumption are essentially limiting their application in mobile and IoT areas. While binary convolutional networks can alleviate these problems, the limited bitwidth of weights is often leading to significant degradation of prediction accuracy. In this paper, we present a method for training binary networks that maintains a stable predefined level of their information capacity throughout the training process by applying Shannon entropy based penalty to convolutional filters. The results of experiments conducted on the SVHN, CIFAR and ImageNet datasets demonstrate that the proposed approach can statistically significantly improve the accuracy of binary networks. (© 2020 Elsevier Ltd)

Publication status

published

Editor

Book title

Volume

138

Pages / Article No.

276 - 281

Publisher

Elsevier

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Deep learning; Binary neural network; Information theory; Shannon entropy

Organisational unit

Notes

Funding

Related publications and datasets