We present a fully memristive spiking neural network (MSNN) consisting of
novel memristive neurons trained using the backpropagation through time (BPTT)
learning rule. Gradient descent is applied directly to the memristive
integrated-and-fire (MIF) neuron designed using analog SPICE circuit models,
which generates distinct depolarization, hyperpolarization, and repolarization
voltage waveforms. Synaptic weights are trained by BPTT using the membrane
potential of the MIF neuron model and can be processed on memristive crossbars.
The natural spiking dynamics of the MIF neuron model are fully differentiable,
eliminating the need for gradient approximations that are prevalent in the
spiking neural network literature. Despite the added complexity of training
directly on SPICE circuit models, we achieve 97.58% accuracy on the MNIST
testing dataset and 75.26% on the Fashion-MNIST testing dataset, the highest
accuracies among all fully MSNNs.

本文提出了一种完全基于 memristive spiking 神经网络的 MSNN，采用 backpropagation through time (BPTT) 学习规则训练了新型 memristive 神经元，并利用 analog SPICE 电路模型直接应用梯度下降的方式来对神经元进行训练，同时实现可处理在 memristive crossbars 上的突触权重训练。

SPICEprop：通过记忆加突触神经元网络反向传播误差

SPICEprop: Backpropagating Errors Through Memristive Spiking Neural Networks

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.

本研究基于 memristive neuron 和 memristive synapse 提出了一个完全基于 memristor 的脉冲神经网络 (MSNN)，并采用无监督的 Spiking Time Dependent Plasticity (STDP) 学习规则。我们通过电路模拟验证了 MSNN 的学习效果，并实现了两种类型的 MSNN 结构：一种是生物学合理的记忆检索系统，另一种是用于多类别分类。