On Study of the Binarized Deep Neural Network for Image Classification

TL;DR

This paper introduces a binarized deep neural network that simplifies all values and calculations to binary form, significantly reducing computational and storage requirements, making it suitable for use on various devices.

Contribution

It proposes a novel binarized neural network focusing on the basic propagation function, enabling efficient deployment on resource-constrained devices.

Findings

The binarized network reduces computational resource usage.

It demonstrates feasibility through experimental results.

The approach enables deployment on devices with limited resources.

Abstract

Recently, the deep neural network (derived from the artificial neural network) has attracted many researchers' attention by its outstanding performance. However, since this network requires high-performance GPUs and large storage, it is very hard to use it on individual devices. In order to improve the deep neural network, many trials have been made by refining the network structure or training strategy. Unlike those trials, in this paper, we focused on the basic propagation function of the artificial neural network and proposed the binarized deep neural network. This network is a pure binary system, in which all the values and calculations are binarized. As a result, our network can save a lot of computational resource and storage. Therefore, it is possible to use it on various devices. Moreover, the experimental results proved the feasibility of the proposed network.