Fast ConvNets Using Group-wise Brain Damage

Understand

We revisit the idea of brain damage, i.e.

• the pruning of the coefficients of a neural network, and suggest how brain damage can be modified and used to speedup convolutional layers.
• The approach uses the fact that many efficient implementations reduce generalized convolutions to matrix multiplications.
• The suggested brain damage process prunes the convolutional kernel tensor in a group-wise fashion by adding group-sparsity regularization to the standard training process.