LGMLJan 14, 2020

Quantisation and Pruning for Neural Network Compression and Regularisation

arXiv:2001.04850v127 citations
AI Analysis

This work addresses efficiency challenges for deploying neural networks on low-powered devices, but it is incremental as it applies existing techniques to standard models.

The paper tackled the problem of reducing computational and memory requirements of deep neural networks for real-time use on consumer hardware by applying pruning and quantisation, achieving compression to less than half the original size and a 7x speedup on MobileNet.

Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered devices. In this paper, we investigate reducing the computational and memory requirements of neural networks through network pruning and quantisation. We examine their efficacy on large networks like AlexNet compared to recent compact architectures: ShuffleNet and MobileNet. Our results show that pruning and quantisation compresses these networks to less than half their original size and improves their efficiency, particularly on MobileNet with a 7x speedup. We also demonstrate that pruning, in addition to reducing the number of parameters in a network, can aid in the correction of overfitting.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes