Fast and Low-Memory Deep Neural Networks Using Binary Matrix Factorization

TL;DR

This paper demonstrates that binary matrix factorization significantly reduces the computational and memory requirements of deep neural networks, enabling more practical deployment.

Contribution

It introduces the use of binary matrix factorization for deep neural networks, showing its effectiveness in resource reduction compared to prior methods.

Findings

Reduces memory usage in neural networks

Decreases computational complexity

Facilitates practical deployment of deep models

Abstract

Despite the outstanding performance of deep neural networks in different applications, they are still computationally extensive and require a great number of memories. This motivates more research on reducing the resources required for implementing such networks. An efficient approach addressed for this purpose is matrix factorization, which has been shown to be effective on different networks. In this paper, we utilize binary matrix factorization and show its great efficiency in reducing the required number of resources in deep neural networks. In effect, this technique can lead to the practical implementation of such networks.