Metaplasticity-Enabled Graphene Quantum Dot Devices for Mitigating Catastrophic Forgetting in Artificial Neural Networks.

Journal: Advanced materials (Deerfield Beach, Fla.)
PMID:

Abstract

The limitations of deep neural networks in continuous learning stem from oversimplifying the complexities of biological neural circuits, often neglecting the dynamic balance between memory stability and learning plasticity. In this study, artificial synaptic devices enhanced with graphene quantum dots (GQDs) that exhibit metaplasticity is introduced, a higher-order form of synaptic plasticity that facilitates the dynamic regulation of memory and learning processes similar to those observed in biological systems. The GQDs-assisted devices utilize interface-mediated modifications in asymmetric conductive pathways, replicating classical synaptic plasticity mechanisms. This allows for repeatable and linearly programmable adjustments to future weight changes linked to historical weights. Incorporating metaplasticity is essential for achieving generalization within deep neural networks, which enables them to adapt more fluidly to new information while retaining previously acquired knowledge. The GQDs-device-based system achieved a 97% accuracy on the fourth MNIST dataset task, while consistently achieving performance levels above 94% on prior tasks. This performance substantiates the feasibility of directly transferring metaplasticity principles to deep neural networks, thereby addressing the challenges associated with catastrophic forgetting. These findings present a promising hardware solution for developing neuromorphic systems with robust and sustained learning capabilities that can effectively bridge the gap between artificial and biological neural networks.

Authors

  • Xuemeng Fan
    School of Integrated Circuits, Zhejiang University, Hangzhou, Zhejiang, 311200, China.
  • Anzhe Chen
    School of Micro-Nano Electronics, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou 310027, China.
  • Zongwen Li
    School of Integrated Circuits, Zhejiang University, Hangzhou, Zhejiang, 311200, China.
  • Zhihao Gong
    ZJU-Hangzhou Global Scientific and Technological Innovation Center, Hangzhou, Zhejiang, 310027, China.
  • Zijian Wang
    School of Medical Informatics Engineering, Anhui University of Chinese Medicine, Hefei, Anhui 230012, China.
  • Guobin Zhang
    School of Mechanical Engineering, Tianjin University, 135 Yaguan Road, Jinnan District, Tianjin, 300350, China.
  • Pengtao Li
    Civil Aviation Key Laboratory of Aircraft Health Monitoring and Intelligent Maintenance, College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China.
  • Yang Xu
    Dermatological Department, Nan Chong Center Hospital, Nanchong, China.
  • Hua Wang
    Department of Orthopaedics, The Second Xiangya Hospital of Central South University, Changsha, Hunan, China.
  • Changhong Wang
    Engineering Product Development Singapore University of Technology and Design 8 Somapah Road, Singapore 487372.
  • Xiaolei Zhu
    School of Information and Artificial Intelligence, Anhui Agricultural University, Hefei, Anhui, China.
  • Rong Zhao
    Pinggu District Center for Disease Control and Prevention, Beijing 101200, China.
  • Bin Yu
    Department of Anesthesiology, Peking University First Hospital, Ningxia Women's and Children's Hospital, Yinchuan, China.
  • Yishu Zhang
    Engineering Product Development, Singapore University of Technology and Design (SUTD), 8 Somapah Road, 487372, Singapore.