Design and Analysis of Real Time Spiking Neural Network Decoder for Neuromorphic Chips
Design and Analysis of Real Time Spiking Neural Network Decoder for Neuromorphic Chips
复制标题
神经形态芯片实时尖峰神经网络解码器的设计与分析
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Y. Yi
中科院分区：
文献类型：
--
作者：
Chenyuan Zhao;Lingjia Liu;Y. Yi
神经形态计算基于模仿生物神经过程的非传统架构，可以在实时数据监控和预测以及资源分配方面提供潜在的颠覆性功能和高能效。设计神经形态芯片的第一步是探索有效的真实的时间和能量有效的脉冲神经网络（SNN）编码器和解码器的设计方法。本文设计并优化了一种基于尖峰时间相关可塑性原理（STDP）的解码器。实验结果表明，基于STDP的SNN解码器在多尺度信息恢复方面具有良好的性能。
Neuromorphic computing, which is based on non-traditional architectures that mimic bio-neurological process, could offer potentially disruptive capabilities and high energy-efficiency in real-time data monitoring and prediction, and resource allocation. The first step for de-signing neuromorphic chips is to explore effective design methodologies for real time and energy efficient spiking neural network (SNN) encoders and decoders. In this paper, a spike timing dependent plasticity principle (STDP) based decoder is designed and optimized. As shown in our experimental results, the proposed STDP based SNN decoder achieves good performance in information recovery with multiple scales.