A brain-inspired algorithm that mitigates catastrophic forgetting of artificial and spiking neural networks with low computational cost

EPOC: A 28-nm 5.3 pJ/SOP Event-Driven Parallel Neuromorphic Hardware With Neuromodulation-Based Online Learning

Bio-inspired neuromorphic hardware with learning ability is highly promising to achieve human-like intelligence, particularly in terms of high energy efficiency and strong environmental adaptability. Though many customized prototypes have demonstrated learning ability, learning on neuromorphic hardware still lacks a bio-plausible and unified learning framework, and inherent spike-based sparsity and parallelism have not been fully exploited, which fundamentally limits their computational efficiency and scale. Therefore, we develop a unified, event-driven, and massively parallel multi-core neuromorphic online learning processor, namely EPOC. We present a neuromodulation-based neuromorphic online learning framework to unify various learning algorithms, and EPOC supports high-accuracy local/global supervised Spike Neural Network (SNN) learning with a low-memory-demand streaming single-sample learning strategy through different neuromodulator formulations. EPOC leverages a novel event-driven computation method that fully exploits spike-based sparsity throughout the forward-backward learning phases, and parallel multi-channel and multi-core computing architecture, bringing 9.9$\times$ time efficiency improvement compared with the baseline architecture. We synthesize EPOC in a 28-nm CMOS process and perform extensive benchmarking. EPOC achieves state-of-the-art learning accuracy of 99.2%, 98.2%, and 94.3% on the MNIST, NMNIST, and DVS-Gesture benchmarks, respectively. Local-learning EPOC achieves 2.9$\times$ time efficiency improvement compared with the global learning counterpart. EPOC operates at a typical clock frequency of 100 MHz, providing a peak 328 GOPS/51 GSOPS throughput and a 5.3 pJ/SOP energy efficiency.

Brain-Inspired Learning, Perception, and Cognition: A Comprehensive Review

The progress of brain cognition and learning mechanisms has provided new inspiration for the next generation of artificial intelligence (AI) and provided the biological basis for the establishment of new models and methods. Brain science can effectively improve the intelligence of existing models and systems. Compared with other reviews, this article provides a comprehensive review of brain-inspired deep learning algorithms for learning, perception, and cognition from microscopic, mesoscopic, macroscopic, and super-macroscopic perspectives. First, this article introduces the brain cognition mechanism. Then, it summarizes the existing studies on brain-inspired learning and modeling from the perspectives of neural structure, cognitive module, learning mechanism, and behavioral characteristics. Next, this article introduces the potential learning directions of brain-inspired learning from four aspects: perception, cognition, understanding, and decision-making. Finally, the top-ten open problems that brain-inspired learning, perception, and cognition currently face are summarized, and the next generation of AI technology has been prospected. This work intends to provide a quick overview of the research on brain-inspired AI algorithms and to motivate future research by illuminating the latest developments in brain science.

Hybrid neural networks for continual learning inspired by corticohippocampal circuits

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.

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

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.

Advancing brain-inspired computing with hybrid neural networks

Brain-inspired computing, drawing inspiration from the fundamental structure and information-processing mechanisms of the human brain, has gained significant momentum in recent years. It has emerged as a research paradigm centered on brain-computer dual-driven and multi-network integration. One noteworthy instance of this paradigm is the hybrid neural network (HNN), which integrates computer-science-oriented artificial neural networks (ANNs) with neuroscience-oriented spiking neural networks (SNNs). HNNs exhibit distinct advantages in various intelligent tasks, including perception, cognition and learning. This paper presents a comprehensive review of HNNs with an emphasis on their origin, concepts, biological perspective, construction framework and supporting systems. Furthermore, insights and suggestions for potential research directions are provided aiming to propel the advancement of the HNN paradigm.