Optimised weight programming for analogue memory-based deep neural networks
oleh: Charles Mackin, Malte J. Rasch, An Chen, Jonathan Timcheck, Robert L. Bruce, Ning Li, Pritish Narayanan, Stefano Ambrogio, Manuel Le Gallo, S. R. Nandakumar, Andrea Fasoli, Jose Luquin, Alexander Friz, Abu Sebastian, Hsinyu Tsai, Geoffrey W. Burr
| Format: | Article |
|---|---|
| Diterbitkan: | Nature Portfolio 2022-06-01 |
Deskripsi
Device-level complexity represents a big shortcoming for the hardware realization of analogue memory-based deep neural networks. Mackin et al. report a generalized computational framework, translating software-trained weights into analogue hardware weights, to minimise inference accuracy degradation.