부산대학교 도서관

Spiking neural networks are a promising candidate for next-generation machine learning and are suitable for power-constrained edge devices. In this brief, we present a mixed-signal neuromorphic processor that efficiently implements an echo state network (ESN) and achieves high accuracy without a costly on-chip training process. The design employs a charge-domain computation circuit that efficiently realizes a leaky integrate and fire neuron. Combined with optimizing sparse connections, the proposed algorithm-hardware co-design approach results in a highly energy-efficient operation while delivering high accuracy. Fabricated in a 65nm LP process, the processor is measured to achieve 95.35% MNIST classification accuracy, which closely matches the software model, and energy efficiency of 12.92nJ per classification.