5 papers
Learned Step Size Quantization
Steven K. Esser, Jeffrey L. McKinstry, Deepika Bablani +2
Deep networks run with low precision operations at inference time offer power and space advantages over high precision alternatives, but need to overcome the challenge of maintaini…
Low Precision Policy Distillation with Application to Low-Power, Real-time Sensation-Cognition-Action Loop with Neuromorphic Computing
Jeffrey L Mckinstry, Davis R. Barch, Deepika Bablani +5
Low precision networks in the reinforcement learning (RL) setting are relatively unexplored because of the limitations of binary activations for function approximation. Here, in th…
Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference
Jeffrey L. McKinstry, Steven K. Esser, Rathinakumar Appuswamy +4
To realize the promise of ubiquitous embedded deep network inference, it is essential to seek limits of energy and area efficiency. To this end, low-precision networks offer tremen…
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…
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…