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.