Highly Reliable Synaptic Cell Array Based on Organic–Inorganic Hybrid Bilayer Stack toward Precise Offline Learning. (13th May 2022)

• Record Type: Journal Article
• Authors: Cha, Jun-Hwe; Jang, Byung Chul; Oh, Jungyeop; Lee, Changhyeon; Yang, Sang Yoon; Park, Hamin; Im, Sung Gap; Choi, Sung-Yool
• Is Part Of: Advanced intelligent systems. Volume 4:Number 6(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-05-13
• Subjects: 5-bit multilevel retention -- conductive-bridging random-access memory (CBRAM) -- fine-tuning -- neuromorphic computing -- offline learning; Artificial intelligence -- Periodicals; Robotics -- Periodicals; Control theory -- Periodicals; 006.3
• DOI: 10.1002/aisy.202200018
• Languages: English
• ISSNs: 2640-4567

Abstract

Abstract : As the use of artificial intelligence (AI) soars, the development of novel neuromorphic computing is demanding because of the disadvantages of the von Neumann architecture. Furthermore, extensive research on electrochemical metallization (ECM) memristors as synaptic cells have been carried out toward a linear conductance update for online learning applications. In most cases, however, a conductance distribution change over time has not been studied as a major issue, giving less consideration to inference‐only computing accelerators based on offline learning. Herein, organic–inorganic bilayer stacking for synaptic unit cells using poly(1, 3, 5‐trivinyl‐1, 3, 5‐trimethyl cyclotrisiloxane) (pV3D3) and Al2 O3 thin films is suggested, showing highly enhanced reliability for offline learning. The bilayer structure achieves better reliability and control of the analog resistive switching and synaptic functions, respectively, through the guided formation of conductive filaments via tip‐enhanced electric fields. In addition, 5‐bit multilevel states achieve long‐term stability (>10 4 s) following an in‐depth study on conductance‐level stability. Finally, a device‐to‐system‐level simulation is performed by building a convolutional neural network (CNN) based on the hybrid devices. This highlighted the significance of multilevel states in fully connected layers. It is believed that the study provides a practical approach to using ECM‐based memristors for inference‐only neural network accelerators. Abstract : An organic–inorganic hybrid bilayer stack (pV3D3/Al2 O3 ) is suggested for a highly reliable synaptic cell toward precise offline learning. The pV3D3/Al2 O3 device shows conductancefine‐tuning with a reasonable dynamic range of 9 and 5‐bit multilevel states over 10 4 s with the average standard deviation of 7.3 μS even below 10G0 .