NoiseOut: A Simple Way to Prune Neural Networks
This addresses the issue of unnecessary computation and memory usage in neural networks for practitioners, but it is incremental as it builds on existing pruning methods.
The paper tackles the problem of over-parameterization in neural networks by proposing NoiseOut, a pruning algorithm based on neuron activation correlation, which achieves high pruning rates while maintaining accuracy on various networks and datasets.
Neural networks are usually over-parameterized with significant redundancy in the number of required neurons which results in unnecessary computation and memory usage at inference time. One common approach to address this issue is to prune these big networks by removing extra neurons and parameters while maintaining the accuracy. In this paper, we propose NoiseOut, a fully automated pruning algorithm based on the correlation between activations of neurons in the hidden layers. We prove that adding additional output neurons with entirely random targets results into a higher correlation between neurons which makes pruning by NoiseOut even more efficient. Finally, we test our method on various networks and datasets. These experiments exhibit high pruning rates while maintaining the accuracy of the original network.