Data-free parameter pruning for Deep Neural Networks
This addresses the need for smaller, more efficient models in computer vision, though it is incremental as it builds on existing pruning methods by focusing on neurons.
The paper tackles the problem of reducing the size of deep neural networks by pruning redundant neurons instead of individual weights, achieving up to 85% parameter reduction in an MNIST-trained network and 35% in AlexNet without significant performance loss.
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.