Hybrid neural networks for continual learning inspired by corticohippocampal circuits.

Journal: Nature communications
PMID:

Abstract

Current artificial systems suffer from catastrophic forgetting during continual learning, a limitation absent in biological systems. Biological mechanisms leverage the dual representation of specific and generalized memories within corticohippocampal circuits to facilitate lifelong learning. Inspired by this, we develop a corticohippocampal circuits-based hybrid neural network (CH-HNN) that emulates these dual representations, significantly mitigating catastrophic forgetting in both task-incremental and class-incremental learning scenarios. Our CH-HNNs incorporate artificial neural networks and spiking neural networks, leveraging prior knowledge to facilitate new concept learning through episode inference, and offering insights into the neural functions of both feedforward and feedback loops within corticohippocampal circuits. Crucially, CH-HNN operates as a task-agnostic system without increasing memory demands, demonstrating adaptability and robustness in real-world applications. Coupled with the low power consumption inherent to SNNs, our model represents the potential for energy-efficient, continual learning in dynamic environments.

Authors

  • Qianqian Shi
  • Faqiang Liu
    Department of Precision Instrument, Tsinghua University, Beijing, 100084, China; Center for Brain Inspired Computing Research, Tsinghua University, Beijing, 100084, China; Beijing Innovation Center for Future Chip, Beijing, 100084, China.
  • Hongyi Li
    State Key Laboratory of Robotics, Shenyang Institute of Automation, University of Chinese Academy of Sciences, Shenyang, Liaoning, P. R. China.
  • Guangyu Li
    Department of Computer Science, University of Southern California, Los Angeles, CA.
  • Luping Shi
    Centre for Brain Inspired Computing Research (CBICR), Department of Precision Instrument, Tsinghua University, Beijing 100084, China.
  • Rong Zhao
    Pinggu District Center for Disease Control and Prevention, Beijing 101200, China.