Exploring Model Stability of Deep Neural Networks for Reliable RRAM-based In-Memory Acceleration

Exploring Model Stability of Deep Neural Networks for Reliable RRAM-based In-Memory Acceleration

RRAM-based in-memory computing (IMC) effectively accelerates deep neural networks (DNNs). Furthermore, model compression techniques, such as quantization and pruning, are necessary to improve algorithm mapping and hardware performance. However, in the presence of RRAM device variations, low-precisio...

Full description

Bibliographic Details
Main Authors: Beckmann, K. (Author), Cady, N.C (Author), Cao, Y. (Author), Du, X. (Author), Fan, D. (Author), Hazra, J. (Author), Joshi, R. (Author), Krishnan, G. (Author), Li, Z. (Author), Liehr, M. (Author), Sun, J. (Author), Yang, L. (Author)
Format: Article
Language:English
Published: IEEE Computer Society 2022
Subjects:
Benchmarking
Computational modeling
Computational modelling
Deep neural networks
Deep Neural Networks
Dynamic random access storage
In-memory computing
In-Memory Computing
Mapping accuracy
Model stability
Model Stability
Neural networks
Neural-networks
Perturbation method
Perturbation methods
Perturbation techniques
Pruning
Quantisation
Quantization
Quantization (signal)
Reliability
Reliability analysis
RRAM
Semiconductor device modeling
Semiconductor devices
Stability
Stability analysis
Stability analyze
Training
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items