Neuron Pruning for Compressing Deep Networks using Maxout Architectures
This provides an efficient method for reducing model size in deep learning applications, though it appears incremental as it builds on existing pruning techniques.
The paper tackles the problem of compressing deep neural networks by pruning entire neurons using maxout architectures and local relevance measurements, achieving network size reductions of up to 74% on MNIST and 61% on LFW without performance loss.
This paper presents an efficient and robust approach for reducing the size of deep neural networks by pruning entire neurons. It exploits maxout units for combining neurons into more complex convex functions and it makes use of a local relevance measurement that ranks neurons according to their activation on the training set for pruning them. Additionally, a parameter reduction comparison between neuron and weight pruning is shown. It will be empirically shown that the proposed neuron pruning reduces the number of parameters dramatically. The evaluation is performed on two tasks, the MNIST handwritten digit recognition and the LFW face verification, using a LeNet-5 and a VGG16 network architecture. The network size is reduced by up to $74\%$ and $61\%$, respectively, without affecting the network's performance. The main advantage of neuron pruning is its direct influence on the size of the network architecture. Furthermore, it will be shown that neuron pruning can be combined with subsequent weight pruning, reducing the size of the LeNet-5 and VGG16 up to $92\%$ and $80\%$ respectively.