Work

A Binary-Activation, Multi-Level Weight RNN and Training Algorithm for ADC-/DAC-Free and Noise-Resilient Processing-in-Memory Inference With eNVM

Year: 2023
Type: article
Abstract: We propose a new algorithm for training neural networks with binary activations and multi-level weights, which enables efficient processing-in-memory circuits with embedded nonvolatile memories (eNVM). Binary activations obviate costly DACs and ADCs. Multi-level weights leverage multi-level eNVM cells. Compared to existing algorithms, our method not only works for feed-forward networks (e.g., fully-connected and convolutional), but also achieves higher accuracy and noise resilience for recurrent networks. In particular, we present an RNN-based trigger-word detection PIM accelerator, with detailed hardware noise models and circuit co-design techniques, and validate our algorithm's high inference accuracy and robustness against a variety of real hardware non-idealities.
Institution: Harvard University
Language: English
Open Access status: green
OpenAlex ID: W3092588265
FWCI: 0.587
Cites: 41
Cited by: 10
Related to: 9