Maqola

Artificial optic-neural synapse for colored and color-mixed pattern recognition

Seunghwan SeoDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, 16419, KoreaSeo-Hyeon JoDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, 16419, KoreaSungho KimDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, 16419, KoreaJaewoo ShimDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, 16419, KoreaSeyong OhDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, 16419, KoreaJeong-Hoon KimDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, 16419, KoreaKeun HeoDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, 16419, KoreaJae-Woong ChoiSKKU Advanced Institute of Nanotechnology (SAINT), Sungkyunkwan University, Suwon, 16417, KoreaChanghwan ChoiDivision of Materials Science and Engineering, Hanyang University, Seoul, 04763, KoreaSaeroonter OhDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, 16419, KoreaDuygu KuzumDepartment of Electrical and Computer Engineering, University of California, San Diego, San Diego, CA, 92093, USAH.‐S. Philip WongDepartment of Electrical Engineering, Stanford University, Stanford, CA, 94305, USAJin‐Hong ParkDepartment of Electrical Engineering, Stanford University, Stanford, CA, 94305, USA. [email protected]

2018en

ABI

Annotatsiya

Abstract The priority of synaptic device researches has been given to prove the device potential for the emulation of synaptic dynamics and not to functionalize further synaptic devices for more complex learning. Here, we demonstrate an optic-neural synaptic device by implementing synaptic and optical-sensing functions together on h -BN/WSe 2 heterostructure. This device mimics the colored and color-mixed pattern recognition capabilities of the human vision system when arranged in an optic-neural network. Our synaptic device demonstrates a close to linear weight update trajectory while providing a large number of stable conduction states with less than 1% variation per state. The device operates with low voltage spikes of 0.3 V and consumes only 66 fJ per spike. This consequently facilitates the demonstration of accurate and energy efficient colored and color-mixed pattern recognition. The work will be an important step toward neural networks that comprise neural sensing and training functions for more complex pattern recognition.

Hali tarjima qilinmagan

Identifikatorlar

DOI: 10.1038/s41467-018-07572-5

Iqtiboslar va manbalar

2 ta iqtibos0 ta foydalanilgan manba

Koʻrsatkichlar — AkademScholar