Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices

TL;DR

This paper introduces Two-Bit Networks (TBNs), a model compression technique for CNNs that enables efficient deployment on resource-limited embedded devices by using weights encoded with only two bits.

Contribution

The paper proposes a novel two-bit weight encoding scheme for CNNs, significantly reducing memory and computation requirements while maintaining accuracy.

Findings

Reduces memory usage substantially

Improves computational efficiency

Maintains competitive classification accuracy

Abstract

With the rapid proliferation of Internet of Things and intelligent edge devices, there is an increasing need for implementing machine learning algorithms, including deep learning, on resource-constrained mobile embedded devices with limited memory and computation power. Typical large Convolutional Neural Networks (CNNs) need large amounts of memory and computational power, and cannot be deployed on embedded devices efficiently. We present Two-Bit Networks (TBNs) for model compression of CNNs with edge weights constrained to (-2, -1, 1, 2), which can be encoded with two bits. Our approach can reduce the memory usage and improve computational efficiency significantly while achieving good performance in terms of classification accuracy, thus representing a reasonable tradeoff between model size and performance.