.png){kind=icon}
返回
Efficient Spiking Neural Networks With Logarithmic Temporal Coding
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2020.2994360.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
A Spiking Neural Network (SNN) can be trained indirectly by first training an Artificial Neural Network (ANN) with the conventional backpropagation algorithm, then converting it into an equivalent SNN. To reduce the computational cost of the resulting SNN as measured by the number of spikes, we present Logarithmic Temporal Coding (LTC), where the number of spikes used to encode an activation grows logarithmically with the activation value; and the accompanying Exponentiate-and-Fire (EF) neuron model, which only involves efficient bit-shift and addition operations. Moreover, we improve the training process of ANN to compensate for approximation errors due to LTC. Experimental results indicate that the resulting SNN achieves competitive performance in terms of classification accuracy at significantly lower computational cost than related work.
Keyword:
Encoding
Training
Biological information theory
Biological neural networks
Computational modeling
Spiking neural networks
temporal coding
neuromorphic computing
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
分享收藏Spiking Deep Convolutional Neural Networks for Energy-Efficient Object RecognitionSpiking深度卷积神经网络用于节能目标识别
PREAI
分享收藏分享收藏Regional colon transit in patients with dys-synergic defaecation or slow transit in patients with constipation.png)
GutOAAI
GutIF0
OAAI分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏Unsupervised AER Object Recognition Based on Multiscale Spatio-Temporal Features and Spiking NeuronsOAAI
OAAI分享收藏
查看更多内容