[1] CHEN G K, KUMAR R, SUMBUL H E, et al. A 4096-neuron 1m-synapse 3.8 pJ/SOP spiking neural network with on-chip STDP learning and sparse weights in 10 nm FinFET CMOS ［C］ // IEEE Symp VLSI Circ. Honolulu, HI, USA. 2018: 255-256.

[2] 尚瑛杰, 董丽亚, 何虎. 基于脉冲神经网络的迁移学习算法与软件框架 ［J］. 计算机工程, 2020, 46(3): 53-59.

[3] INDIVERI G, CHICCA E, DOUGLAS R. A VLSI array of low-power spiking neurons and bistable synapses with spike-timing dependent plasticity ［J］. IEEE Trans Neural Networks, 2006, 17(1): 211-221.

[4] CRUZ-ALBRECHT J M, YUNG M W, SRINIVASA N. Energy-efficient neuron, synapse and STDP integrated circuits ［J］. IEEE Trans Biomedical Circ Syst, 2012, 6(3): 246-256.

[5] IVANS R C, CANTLEY K D, SHUMAKER J L. A CMOS synapse design implementing tunable asymmetric spike timing-dependent plasticity ［C］ // IEEE Int Midwest Symp Circ Syst. Boston, MA, USA. 2017: 1125-1128.

[6] MARKRAM H, LUBKE J, FROTSCHER M, et al. Regulation of synaptic efficacy by coincidence of postsynaptic APs and EPSPs ［J］. Science, 1997, 275(5297): 213-215.

[7] SJOSTROM J, GERSTNER W. Spike-timing dependent plasticity ［J］. Neuroreport, 2010, 71(79): 1694-1704.

[8] ZHANG L I, TAO H W, HOLT C E, et al. A critical window for cooperation and competition among developing retinotectal synapses ［J］. Nature, 1998, 395(6697): 37-44.

[9] PHONG N D B, DANESHTALAB M, DYTCKOV S, et al. Silicon synapse designs for VLSI neuromorphic platform ［C］ // NORCHIP. Tampere, Finland. 2014: 1-6.

[10] SAXENA V, WU X, ZHU K. Energy-efficient CMOS memristive synapses for mixed-signal neuromorphic system-on-a-chip ［C］ // Proceed IEEE Int Symp Circ Syst. Florence, Italy. 2018: 1-5.

[11] HUAN C, WANG Y, CUI X, et al. A reconfigurable mixed signal CMOS design for multiple STDP learning rules ［C］ // IEEE 3rd Int Conf Elec Tech. Chengdu, China. 2020: 639-643.