4 accepted papers
Inducing and leveraging sparse activations during training and inference is a promising avenue for improving the computational efficiency of deep networks, which is increasingly important as network sizes continue to grow and their application becomes more widespread. Here we use the large width Ga…
The requirement to repeatedly move large feature maps off-and on-chip during inference with convolutional neural networks (CNNs) imposes high costs in energy and time. In this work we explore an improved method for compressing all feature maps of pre-trained CNNs to below a specified limit. This is…
Accurately forecasting extreme rainfall is notoriously difficult, but is also ever more crucial for society as climate change increases the frequency of such extremes. Global numerical weather prediction models often fail to capture extremes, and are produced at too low a resolution to be actionable…
That neural networks may be pruned to high sparsities and retain high accuracy is well established. Recent research efforts focus on pruning immediately after initialization so as to allow the computational savings afforded by sparsity to extend to the training process. In this work, we introduce a…