Optogenetics inspired transition metal dichalcogenide neuristors for in-memory deep recurrent neural networks

Rohit Abraham John, Jyotibdha Acharya, Chao Zhu, Abhijith Surendran, Sumon Kumar Bose, Apoorva Chaturvedi, Nidhi Tiwari, Yang Gao, Yongmin He, Keke K. Zhang, Manzhang Xu, Wei Lin Leong, Zheng Liu, Arindam Basu () and Nripan Mathews ()
Additional contact information
Rohit Abraham John: Nanyang Technological University
Jyotibdha Acharya: Nanyang Technological University
Chao Zhu: Nanyang Technological University
Abhijith Surendran: Nanyang Technological University
Sumon Kumar Bose: Nanyang Technological University
Apoorva Chaturvedi: Nanyang Technological University
Nidhi Tiwari: Nanyang Technological University
Yang Gao: Nanyang Technological University
Yongmin He: Nanyang Technological University
Keke K. Zhang: Nanyang Technological University
Manzhang Xu: Nanyang Technological University
Wei Lin Leong: Nanyang Technological University
Zheng Liu: Nanyang Technological University
Arindam Basu: Nanyang Technological University
Nripan Mathews: Nanyang Technological University

Nature Communications, 2020, vol. 11, issue 1, 1-9

Abstract: Abstract Shallow feed-forward networks are incapable of addressing complex tasks such as natural language processing that require learning of temporal signals. To address these requirements, we need deep neuromorphic architectures with recurrent connections such as deep recurrent neural networks. However, the training of such networks demand very high precision of weights, excellent conductance linearity and low write-noise- not satisfied by current memristive implementations. Inspired from optogenetics, here we report a neuromorphic computing platform comprised of photo-excitable neuristors capable of in-memory computations across 980 addressable states with a high signal-to-noise ratio of 77. The large linear dynamic range, low write noise and selective excitability allows high fidelity opto-electronic transfer of weights with a two-shot write scheme, while electrical in-memory inference provides energy efficiency. This method enables implementing a memristive deep recurrent neural network with twelve trainable layers with more than a million parameters to recognize spoken commands with >90% accuracy.

Date: 2020
References: Add references at CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
https://www.nature.com/articles/s41467-020-16985-0 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:11:y:2020:i:1:d:10.1038_s41467-020-16985-0

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-020-16985-0

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().