Date of Award

5-2019

Document Type

Thesis open access

Department

Computer Science

First Advisor

Yu Zhang

Second Advisor

Albert Xin Jiang

Third Advisor

Matthew Hibbs

Abstract

The rising ubiquity of Convolutional Neural Networks for learning tasks has led to their use on a variety of devices. CNNs can be used on small devices, such as phones or embedded systems; however, compute time is a critical enabling factor. On these devices, trading high accuracy for improved performance may be worthwhile. This has led to active research in high-level convolution optimizations. One successful class of optimizations is filter pruning, in which filters that are determined to have a small effect on the network's output are deleted. In this work, we present a self-pruning convolution that is intended to accelerate convolutions for use on small devices. We call it an ALSH Convolution because it uses Asymmetric Locality Sensitive Hashing to generate a subset of the convolution's filters that are likely to produce large outputs for a given input. Our methodology is accessible: it generalizes well to many architectures and is easy to use, essentially functioning as a regular layer. Experiments show that a network modified to use ALSH Convolutions can stay within 5% accuracy on CIFAR-10 and 10% on CIFAR-100. Further, on small devices, a network built with our implementation can be 2x faster than the same network composed of PyTorch's convolution.

Download

Share

COinS