Deep neural networks are robust to weight binarization and other non-linear distortions

no code implementations • 7 Jun 2016 • Paul Merolla, Rathinakumar Appuswamy, John Arthur, Steve K. Esser, Dharmendra Modha

Recent results show that deep neural networks achieve excellent performance even when, during training, weights are quantized and projected to a binary representation.

Binarization Data Augmentation +1

Backpropagation for Energy-Efficient Neuromorphic Computing

no code implementations • NeurIPS 2015 • Steve K. Esser, Rathinakumar Appuswamy, Paul Merolla, John V. Arthur, Dharmendra S. Modha

Solving real world problems with embedded neural networks requires both training algorithms that achieve high performance and compatible hardware that runs in real time while remaining energy efficient.