arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.01416cs.NEcs.AIcs.ET
收藏

具有无监督学习的全忆阻脉冲神经网络

A Fully Memristive Spiking Neural Network with Unsupervised Learning

University of Michigan(密歇根大学);University of Western Australia(西澳大学)

Peng Zhou, Dong-Uk Choi, Jason K. Eshraghian, Sung-Mo Kang

摘要:

我们提出了一个完全忆阻的脉冲神经网络(MSNN)的物理可实现的忆阻神经元和忆阻突触实现无监督的尖峰时间依赖可塑性(STDP)的学习规则。该系统是完全忆阻的,因为神经元和突触动力学都可以通过使用忆阻器来实现。该神经元使用SPICE级忆阻集成和激发(MIF)模型实现,该模型由实现不同去极化、超极化和复极化电压波形所需的最少数量的电路元件组成。所提出的MSNN唯一地实现STDP学习,通过使用来自突触上的电压波形变化的忆阻突触中的累积权重变化,所述电压波形变化在训练过程中由突触前和突触后尖峰电压信号引起。两种类型的MSNN架构进行了研究:1)一个生物合理的记忆检索系统,和2)多类分类系统。我们的电路仿真结果验证了MSNN的无监督学习的有效性,通过复制生物记忆检索机制,并实现了97.5%的准确率在4-模式识别问题在一个大规模的歧视MSNN。

英文摘要:

We present a fully memristive spiking neural network (MSNN) consisting of physically-realizable memristive neurons and memristive synapses to implement an unsupervised Spiking Time Dependent Plasticity (STDP) learning rule. The system is fully memristive in that both neuronal and synaptic dynamics can be realized by using memristors. The neuron is implemented using the SPICE-level memristive integrate-and-fire (MIF) model, which consists of a minimal number of circuit elements necessary to achieve distinct depolarization, hyperpolarization, and repolarization voltage waveforms. The proposed MSNN uniquely implements STDP learning by using cumulative weight changes in memristive synapses from the voltage waveform changes across the synapses, which arise from the presynaptic and postsynaptic spiking voltage signals during the training process. Two types of MSNN architectures are investigated: 1) a biologically plausible memory retrieval system, and 2) a multi-class classification system. Our circuit simulation results verify the MSNN's unsupervised learning efficacy by replicating biological memory retrieval mechanisms, and achieving 97.5% accuracy in a 4-pattern recognition problem in a large scale discriminative MSNN.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑