Hybrid neural networks for continual learning inspired by corticohippocampal circuits
Qianqian Shi, Faqiang Liu, Hongyi Li, Guangyu Li, Luping Shi, Rong Zhao
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. Energy-efficient, task-agnostic continual learning is a key challenge in Artificial Intelligence frameworks. Here, authors propose a hybrid neural network that emulates dual representations in corticohippocampal circuits, reducing the effect of catastrophic forgetting.