当前位置: X-MOL 学术IEEE Signal Proc. Mag. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications
IEEE Signal Processing Magazine ( IF 14.9 ) Pub Date : 2019-11-01 , DOI: 10.1109/msp.2019.2935234
Hyeryung Jang , Osvaldo Simeone , Brian Gardner , Andre Gruning

Spiking neural networks (SNNs) are distributed trainable systems whose computing elements, or neurons, are characterized by internal analog dynamics and by digital and sparse synaptic communications. The sparsity of the synaptic spiking inputs and the corresponding event-driven nature of neural processing can be leveraged by energy-efficient hardware implementations, which can offer significant energy reductions as compared to conventional artificial neural networks (ANNs). The design of training algorithms for SNNs, however, lags behind hardware implementations: most existing training algorithms for SNNs have been designed either for biological plausibility or through conversion from pretrained ANNs via rate encoding.

中文翻译:

概率尖峰神经网络简介:概率模型、学习规则和应用

尖峰神经网络 (SNN) 是分布式可训练系统,其计算元素或神经元的特征在于内部模拟动态以及数字和稀疏突触通信。高能效硬件实现可以利用突触尖峰输入的稀疏性和神经处理的相应事件驱动性质,与传统的人工神经网络 (ANN) 相比,可以显着降低能耗。然而,SNN 训练算法的设计落后于硬件实现:大多数现有的 SNN 训练算法都是针对生物学合理性或通过速率编码从预训练的 ANN 进行转换而设计的。
更新日期:2019-11-01
down
wechat
bug