Energy Efficient Temporal Spatial Information Processing Circuits Based on STDP and Spike Iteration
Energy Efficient Temporal Spatial Information Processing Circuits Based on STDP and Spike Iteration
复制标题
基于 STDP 和 Spike 迭代的节能时空信息处理电路
DOI：
10.1109/tcsii.2019.2945690
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Yang Yi
中科院分区：
文献类型：
--
作者：
Chenyuan Zhao;Qiyuan An;Kangjun Bai;B. Wysocki;Clare D. Thiem;Lingjia Liu;Yang Yi
在这篇简报中，我们提出了一种新的节能时空信息处理电路，作为尖峰神经网络的信号预处理接口。为了将感觉信息转化为高效的类神经元锋电位序列，设计并分析了一种基于迭代编码方案的时空锋电位间隔编码器。此外，解码器的设计与尖峰定时相关的可塑性（STDP）的原则，它表现出良好的信息恢复。提出了ISI编码器的原型，通过标准的180 nm CMOS工艺与3间隔编码器。该ISI编码器可以工作在<inline-formula><tex-math notation="LaTeX">1 MHz</tex-math></inline-formula>采样频率下，芯片面积仅为<inline-formula><tex-math notation="LaTeX">0.647 m ^{2}$</tex-math></inline-formula>，功耗仅<inline-formula><tex-math notation="LaTeX">为1.63 μ W</tex-math></inline-formula>/神经元。本文还设计了一个具有尖峰宽度自适应的多级ISI解码器，并通过CIFAR 10图像数据集进行了评估。
In this brief, we propose a novel energy-efficient temporal-spatial information processing circuit that serves as the signal pre-processing interface for spiking neural networks. In order to transform sensory information into a highly efficient neural-like spike train, an iteration encoding scheme based temporal-spatial inter-spike interval (ISI) encoder is designed and analyzed. Moreover, a decoder is designed with the spike-timing-dependent plasticity (STDP) principle, which performs well in information recovery. The prototype of the proposed ISI encoder is presented, with a 3-interval encoder through the standard 180nm CMOS technology. The proposed ISI encoder could operate in <inline-formula> <tex-math notation="LaTeX">$1{MHz}$ </tex-math></inline-formula> sampling frequency, and it occupies merely <inline-formula> <tex-math notation="LaTeX">$0.647{m}{m}^{2}$ </tex-math></inline-formula> die area while consuming as low as <inline-formula> <tex-math notation="LaTeX">$1.63{uW}$ </tex-math></inline-formula>/neuron power. A multi-level ISI decoder with spike width adaptation is also designed and evaluated through the CIFAR10 image dataset.
超越 STDP 的硅学习：基于钙动力学的多因素突触可塑性的神经形态实现
DOI：
10.1109/tcsi.2016.2616169
发表时间：
2016
期刊：
IEEE Transactions on Circuits and Systems I: Regular Papers
影响因子：
--
作者：
Maldonado Huayaney;Chicca
通讯作者：
Chicca