稀疏二维突触和CMOS神经元混合神经形态硬件用于字符识别

Hybrid neuromorphic hardware with sparing 2D synapse and CMOS neuron for character recognition

神经形态计算能够有效处理数密集型任务.本文提出一种基于二维MoS2突触和CMOS神经元混合集成的神经形态硬件系统,可兼具二维突触器件的灵活可塑性与CMOS神经元的成熟度、可靠性.受益于混合集成,进一步提出特征提取和频率编码方式,降低了硬件所需的突触与神经元数量;基于板级全硬件实现高准确率(98.8%)和低功耗(11.4μW)的字符识别功能.本工作为构建高面积效率和能量效率的神经形态硬件系统提供了一个可行的方案.

Neuromorphic computing enables efficient processing of data-intensive tasks,but requires numerous artificial synapses and neurons for certain functions,which leads to bulky systems and energy challenges.Achieving functionality with fewer synapses and neurons will facilitate integration density and computility.Two-dimensional(2D)materials exhibit potential for artificial synapses,including diverse biomimetic plasticity and efficient computing.Considering the complexity of neuron circuits and the maturity of complementary metal-oxide-semiconductor(CMOS),hybrid integration is attractive.Here,we demonstrate a hybrid neuromorphic hardware with 2D MoS_(2)synaptic arrays and CMOS neural circuitry integrated on board.With the joint benefit of hybrid integration,frequency coding and feature extraction,a total cost of twelve MoS2 synapses,three CMOS neurons,combined with digital/analogue converter enables alphabetic and numeric recognition.MoS_(2)synapses exhibit progressively tunable weight plasticity,CMOS neurons integrate and fire frequency-encoded spikes to display the target characters.The synapse-and neuron-saving hybrid hardware exhibits a competitive accuracy of 98.8%and single recognition energy consumption of 11.4μW.This work provides a viable solution for building neuromorphic hardware with high compactness and computility.