Accurate Inference With Inaccurate RRAM Devices: A Joint Algorithm-Design Solution

Resistive random access memory (RRAM) is a promising technology for energy-efficient neuromorphic accelerators. However, when a pretrained deep neural network (DNN) model is programmed to an RRAM array for inference, the model suffers from accuracy degradation due to RRAM nonidealities, such as devi...

Полное описание

Библиографические подробности

Главные авторы:	Gouranga Charan, Abinash Mohanty, Xiaocong Du, Gokul Krishnan, Rajiv V. Joshi, Yu Cao
Формат:	Artigo
Язык:	Inglês
Опубликовано:	IEEE 2020-01-01
Серии:	IEEE Journal on Exploratory Solid-State Computational Devices and Circuits
Предметы:	Convolution neural networks device nonidealities model robustness neuromorphic computing random sparse adaptation (RSA) resistive random access memory (RRAM)
Online-ссылка:	https://ieeexplore.ieee.org/document/9069242/
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!