DropNeuron: Simplifying the Structure of Deep Neural Networks

TL;DR

DropNeuron introduces a regularization technique that simplifies deep neural networks during training by dropping neurons, maintaining performance while reducing complexity and computational cost.

Contribution

It presents a novel regularization method enabling neural network simplification during training, which was not previously available.

Findings

Effective neuron dropping in various neural network architectures

Maintains performance with reduced network complexity

Open-source implementation available

Abstract

Deep learning using multi-layer neural networks (NNs) architecture manifests superb power in modern machine learning systems. The trained Deep Neural Networks (DNNs) are typically large. The question we would like to address is whether it is possible to simplify the NN during training process to achieve a reasonable performance within an acceptable computational time. We presented a novel approach of optimising a deep neural network through regularisation of net- work architecture. We proposed regularisers which support a simple mechanism of dropping neurons during a network training process. The method supports the construction of a simpler deep neural networks with compatible performance with its simplified version. As a proof of concept, we evaluate the proposed method with examples including sparse linear regression, deep autoencoder and convolutional neural network. The valuations demonstrate excellent performance. The code for this work can be found in http://www.github.com/panweihit/DropNeuron