4 citations · 4 across the 2 of their papers we have counts for
Showing 2016Show all
2 papers · 1 filter
cs.NE2016
Structured Convolution Matrices for Energy-efficient Deep learning
Rathinakumar Appuswamy, Tapan Nayak, John Arthur +6
We derive a relationship between network representation in energy-efficient neuromorphic architectures and block Toplitz convolutional matrices. Inspired by this connection, we dev…
cs.NE2016
Deep neural networks are robust to weight binarization and other non-linear distortions
Paul Merolla, Rathinakumar Appuswamy, John Arthur +2
Recent results show that deep neural networks achieve excellent performance even when, during training, weights are quantized and projected to a binary representation. Here, we sho…