DropNeuron: Simplifying the Structure of Deep Neural Networks
This addresses the issue of large, computationally expensive deep neural networks for machine learning practitioners, offering a method to create simpler networks with comparable performance, though it appears incremental as it builds on existing regularization techniques.
The paper tackles the problem of simplifying deep neural networks during training to reduce size while maintaining performance, proposing DropNeuron, a regularization method that drops neurons, and demonstrates excellent results in evaluations including sparse linear regression, deep autoencoder, and convolutional neural networks.
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