TY - GEN
T1 - Advanced synaptic transistor device towards AI application in hardware perspective
AU - Zhao, Chun
AU - Zhao, Tianshi
AU - Cao, Yixin
AU - Liu, Yina
AU - Yang, Li
AU - Mitrovic, Ivona Z.
AU - Lim, Eng Gee
AU - Zhao, Ce Zhou
N1 - Funding Information:
III. CONCLUSION AND PERSPECTIVE As discussed above the synaptic transistors have been demonstrated to have a high degree of fit with the artificial neural network system. However, there is still many challenges need to be overcome in future. First, up till now, the research on the application of synaptic devices in complex neural network systems is still at the simulation level. To establish a hardware brain-like neuromorphic system, the reliable large-scale fabrication processes are needed. In addition, for a multi-layer computing network, the size of the node may reach the order of one million. Therefore, how to reduce the influence of parasitic effects and energy consumption are also important issues that needs to be considered. Finally, the 3rd generation of neural network, spiking neural network (SNN), has been proved to have more biological plausibility than the conventional ANN system. The spike-time-dependent-plasticity (STDP) learning property is regarded as the core property of linking the synaptic transistors with the units for SNN systems, which is still lack of research. Although, there are still many problems to be solved, the bright prospects of synaptic ACKNOWLEDGMENT This research was funded in part by the Natural Science Foundation of the Jiangsu Higher Education Institutions of China Program (19KJB510059), Na`tural Science Foundation of Jiangsu Province of China (BK20180242), the Suzhou Science and Technology Development Planning Project: Key Industrial Technology Innovation (SYG201924), and the Key Program Special Fund in XJTLU (KSF-P-02, KSF-T-03, KSF-A-04, KSF-A-05, KSF-A-07, KSF-A-18). The author Ivona Z. Mitrovic acknowledges the British Council UKIERI project no. IND/CONT/G/17-18/18.)
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - For the past decades, the synaptic devices for the inmemory computing have been widely investigated due to the high-efficiency computing potential and the ability to mimic biological neurobehavior. However, the conventional twoterminal synaptic memristors show drawbacks of resistance reduction caused by large-scale paralleling and asynchronous storage-reading process, which limit its development. Recently, researchers have paid attention to the transistor-like artificial synapse. Due to the existence of insulator layer and the separation of input and read terminals, the three-terminal synaptic transistors are believed to have greater potential towards artificial intelligence (AI) application fields. In this work, a summary of recent progresses and the future challenges of synaptic transistors are discussed.
AB - For the past decades, the synaptic devices for the inmemory computing have been widely investigated due to the high-efficiency computing potential and the ability to mimic biological neurobehavior. However, the conventional twoterminal synaptic memristors show drawbacks of resistance reduction caused by large-scale paralleling and asynchronous storage-reading process, which limit its development. Recently, researchers have paid attention to the transistor-like artificial synapse. Due to the existence of insulator layer and the separation of input and read terminals, the three-terminal synaptic transistors are believed to have greater potential towards artificial intelligence (AI) application fields. In this work, a summary of recent progresses and the future challenges of synaptic transistors are discussed.
KW - artificial intelligence
KW - artificial synapses
KW - hardware neural network
KW - transistors
UR - http://www.scopus.com/inward/record.url?scp=85123579266&partnerID=8YFLogxK
U2 - 10.1109/ICICDT51558.2021.9626511
DO - 10.1109/ICICDT51558.2021.9626511
M3 - Conference Proceeding
AN - SCOPUS:85123579266
T3 - 2021 International Conference on IC Design and Technology, ICICDT 2021
BT - 2021 International Conference on IC Design and Technology, ICICDT 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 International Conference on IC Design and Technology, ICICDT 2021
Y2 - 15 September 2021 through 17 September 2021
ER -