no code implementations • 30 Jan 2023 • Deepika Bablani, Jeffrey L. McKinstry, Steven K. Esser, Rathinakumar Appuswamy, Dharmendra S. Modha
Using EAGL and ALPS for layer precision selection, full-precision accuracy is recovered with a mix of 4-bit and 2-bit layers for ResNet-50, ResNet-101 and BERT-base transformer networks, demonstrating enhanced performance across the entire accuracy-throughput frontier.
8 code implementations • ICLR 2020 • Steven K. Esser, Jeffrey L. McKinstry, Deepika Bablani, Rathinakumar Appuswamy, Dharmendra S. Modha
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 maintaining high accuracy as precision decreases.
Ranked #1 on Model Compression on ImageNet
no code implementations • ICLR 2019 • Jeffrey L. McKinstry, Steven K. Esser, Rathinakumar Appuswamy, Deepika Bablani, John V. Arthur, Izzet B. Yildiz, Dharmendra S. Modha
Therefore, we (a) reduce solution distance by starting with pretrained fp32 precision baseline networks and fine-tuning, and (b) combat gradient noise introduced by quantization by training longer and reducing learning rates.
no code implementations • 8 Jun 2016 • Rathinakumar Appuswamy, Tapan Nayak, John Arthur, Steven Esser, Paul Merolla, Jeffrey Mckinstry, Timothy Melano, Myron Flickner, Dharmendra Modha
We derive a relationship between network representation in energy-efficient neuromorphic architectures and block Toplitz convolutional matrices.
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.
no code implementations • 28 Mar 2016 • Steven K. Esser, Paul A. Merolla, John V. Arthur, Andrew S. Cassidy, Rathinakumar Appuswamy, Alexander Andreopoulos, David J. Berg, Jeffrey L. McKinstry, Timothy Melano, Davis R. Barch, Carmelo Di Nolfo, Pallab Datta, Arnon Amir, Brian Taba, Myron D. Flickner, Dharmendra S. Modha
Deep networks are now able to achieve human-level performance on a broad spectrum of recognition tasks.
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.