Data-free parameter pruning for Deep Neural Networks

TL;DR

This paper introduces a neuron-level pruning method for deep neural networks that removes redundant neurons to significantly reduce model size without compromising accuracy.

Contribution

It proposes a systematic neuron removal approach based on redundancy, enabling substantial parameter reduction in trained networks.

Findings

Up to 85% parameter reduction in MNIST network

Approximately 35% reduction in AlexNet

Method applicable to most networks with fully connected layers

Abstract

Deep Neural nets (NNs) with millions of parameters are at the heart of many state-of-the-art computer vision systems today. However, recent works have shown that much smaller models can achieve similar levels of performance. In this work, we address the problem of pruning parameters in a trained NN model. Instead of removing individual weights one at a time as done in previous works, we remove one neuron at a time. We show how similar neurons are redundant, and propose a systematic way to remove them. Our experiments in pruning the densely connected layers show that we can remove upto 85\% of the total parameters in an MNIST-trained network, and about 35\% for AlexNet without significantly affecting performance. Our method can be applied on top of most networks with a fully connected layer to give a smaller network.