CMOS-Memristor Hybrid Design of A Neuromorphic Crossbar Array with Integrated Inference and Training DOI

Sarah Johari,

Arghavan Mohammadhassani,

M. Lakshmi Varshika

et al.

2022 IEEE 65th International Midwest Symposium on Circuits and Systems (MWSCAS), Journal Year: 2024, Volume and Issue: unknown, P. 442 - 446

Published: Aug. 11, 2024

Language: Английский

Advancements in 2D layered material memristors: unleashing their potential beyond memory DOI Creative Commons
Kiran A. Nirmal, Dhananjay D. Kumbhar,

Arul Varman Kesavan

et al.

npj 2D Materials and Applications, Journal Year: 2024, Volume and Issue: 8(1)

Published: Dec. 21, 2024

The scalability of two-dimensional (2D) materials down to a single monolayer offers exciting prospects for high-speed, energy-efficient, scalable memristors. This review highlights the development 2D material-based memristors and potential applications beyond memory, including neuromorphic, in-memory, in-sensor, complex computing. also encompasses challenges future opportunities advancing these technologies, underscoring transformative impact on versatile sustainable electronic devices systems.

Language: Английский

Citations

2

Field-free multistate spin–orbit torque devices for programmable image edge recognition circuit DOI
Liu Yang, Wen‐Di Li, Chao Zuo

et al.

Applied Physics Letters, Journal Year: 2024, Volume and Issue: 125(10)

Published: Sept. 2, 2024

The application of spin–orbit torque (SOT) devices to neuromorphic computing platforms is focused on the development hardware circuit architectures. However, inter-device variability, integration modes and peripheral circuits, appropriate scenarios are still unclear, limiting SOT in computing. To solve this problem, paper first proposes a compensation scheme for difference resistance values devices, which solves variability problem at level. Moreover, synergistic with developed based correspondence between multistate characteristics convolutional algorithm. achieve this, multichannel kernel architecture built, implements an image edge recognition application. Finally, simulation model, our CoPt-SOT implemented, capable performing accuracy 96.33%. This provides technical support prospects neural network applications.

Language: Английский

Citations

1

CMOS-Memristor Hybrid Design of A Neuromorphic Crossbar Array with Integrated Inference and Training DOI

Sarah Johari,

Arghavan Mohammadhassani,

M. Lakshmi Varshika

et al.

2022 IEEE 65th International Midwest Symposium on Circuits and Systems (MWSCAS), Journal Year: 2024, Volume and Issue: unknown, P. 442 - 446

Published: Aug. 11, 2024

Language: Английский

Citations

0