Conference paper
Bit Error Robustness for Energy-Efficient DNN Accelerators
David Stutz, Nandhini Chandramoorthy, et al.
MLSys 2021
Invited talk
Developing Analog Hardware for Cloud and Edge Computing
Abstract
In this invited talk, an overview of the Analog AI project is shown, with details of the 14-nm inference chip based on Phase-Change Memory technology. After showing an end-to-end demo, additional details on other network architectures for Analog AI are provided.
Related
Juan Miguel De Haro, Rubén Cano, et al.
IPDPS 2022
Eric A. Joseph
AVS 2023
Irem Boybat-Kara, Benedikt Kersting, et al.
IEDM 2021