An Ultralow Power LixTiO2‐Based Synaptic Transistor for Scalable Neuromorphic Computing. (23rd September 2022)
- Record Type:
- Journal Article
- Title:
- An Ultralow Power LixTiO2‐Based Synaptic Transistor for Scalable Neuromorphic Computing. (23rd September 2022)
- Main Title:
- An Ultralow Power LixTiO2‐Based Synaptic Transistor for Scalable Neuromorphic Computing
- Authors:
- Nguyen, Ngoc‐Anh
Schneegans, Olivier
Salot, Raphaël
Lamy, Yann
Giapintzakis, John
Mai, Van Huy
Oukassi, Sami - Abstract:
- Abstract: Artificial synapses based on electrochemical synaptic transistors (SynTs) have attracted tremendous attention toward massive parallel computing operations. However, most SynTs still suffer from downscaling limitations and high energy consumption. To overcome such drawbacks, a complementary metal–oxide–semiconductor (CMOS) back‐end‐of‐line compatible solid‐state SynT is presented, which includes an ultrathin (10 nm thick) quasiamorphous Li x TiO2 channel. A nonvolatile conductance modulation (<75 nS) is achieved through reversible lithium intercalation into the channel, and synaptic functions, such as long‐term potentiation/depression involve ultralow switching energy of 2 fJ µm −2 . Moreover, this SynT shows excellent endurance (>10 5 weight updates) and recognition accuracy (>95% on the MNIST data test using crossbar simulations). Furthermore, a comprehensive electrochemical study allows deeper insight into the specific pseudocapacitive mechanism at the origin of conductance modulation. These results underline the high potential of Li x TiO2 ‐based SynTs for energy‐efficient neuromorphic applications. Abstract : The all‐solid‐state electrochemical synaptic transistor is fabricated on silicon wafer using complementary metal–oxide–semiconductor (CMOS) microfabrication techniques. The synaptic plasticity is demonstrated by intercalating Li + ions via a LiPON electrolyte into a 10 nm Li x TiO2 channel. This enables highly reversible analog state modulation with 2 fJAbstract: Artificial synapses based on electrochemical synaptic transistors (SynTs) have attracted tremendous attention toward massive parallel computing operations. However, most SynTs still suffer from downscaling limitations and high energy consumption. To overcome such drawbacks, a complementary metal–oxide–semiconductor (CMOS) back‐end‐of‐line compatible solid‐state SynT is presented, which includes an ultrathin (10 nm thick) quasiamorphous Li x TiO2 channel. A nonvolatile conductance modulation (<75 nS) is achieved through reversible lithium intercalation into the channel, and synaptic functions, such as long‐term potentiation/depression involve ultralow switching energy of 2 fJ µm −2 . Moreover, this SynT shows excellent endurance (>10 5 weight updates) and recognition accuracy (>95% on the MNIST data test using crossbar simulations). Furthermore, a comprehensive electrochemical study allows deeper insight into the specific pseudocapacitive mechanism at the origin of conductance modulation. These results underline the high potential of Li x TiO2 ‐based SynTs for energy‐efficient neuromorphic applications. Abstract : The all‐solid‐state electrochemical synaptic transistor is fabricated on silicon wafer using complementary metal–oxide–semiconductor (CMOS) microfabrication techniques. The synaptic plasticity is demonstrated by intercalating Li + ions via a LiPON electrolyte into a 10 nm Li x TiO2 channel. This enables highly reversible analog state modulation with 2 fJ µm − 2 ultralow energy consumption per switching operation. The Li x TiO2 pseudocapacitive behavior allows millisecond conductance switching in all‐solid‐state configuration. … (more)
- Is Part Of:
- Advanced Electronic Materials. Volume 8:Number 12(2022)
- Journal:
- Advanced Electronic Materials
- Issue:
- Volume 8:Number 12(2022)
- Issue Display:
- Volume 8, Issue 12 (2022)
- Year:
- 2022
- Volume:
- 8
- Issue:
- 12
- Issue Sort Value:
- 2022-0008-0012-0000
- Page Start:
- n/a
- Page End:
- n/a
- Publication Date:
- 2022-09-23
- Subjects:
- electrochemical reactions -- electronic devices -- neuromorphic computing -- surfaces interfaces and thin films -- synaptic transistors
Materials -- Electric properties -- Periodicals
Materials science -- Periodicals
Magnetic materials -- Periodicals
Electronic apparatus and appliances -- Periodicals
537 - Journal URLs:
- http://onlinelibrary.wiley.com/journal/10.1002/(ISSN)2199-160X ↗
http://onlinelibrary.wiley.com/ ↗ - DOI:
- 10.1002/aelm.202200607 ↗
- Languages:
- English
- ISSNs:
- 2199-160X
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 0696.848400
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 24673.xml