尖峰神经网络 [英] Spiking neural networks
问题描述
在尖峰神经网络领域应该从哪本书开始?我知道 Gerstner 的 "尖峰神经元模型",2002 年出版.有没有更新的书,或者更合适的书?我有数学和人工神经网络的背景.
Which is the book one should start with in the domain of spiking neural networks? I know about Gerstner's "Spiking Neuron Models", published in 2002. Is there a more recent book, or maybe a more suitable one? I have a background in maths and artificial neural networks.
如果这个领域有一些好的文章或概述,也将它们添加到列表中.
If there are some good articles or overviews in this domain, also add them to the list.
谢谢.
后期编辑
卡雷尔的回答:
" 这取决于你说的尖峰神经网络是什么意思——有至少有几个基本观点.郭士纳代表第一个一 - 他专注于生物神经元的建模.还有他的书从 2002 年开始是理解生物物理的好起点神经元模型.过去也有可能找到这本书在 html ..
" It depends what do you mean by spiking neural networks - there are at least several basic points of view. Gerstner represents the first one - he is focused on modelling of biological neurons. And his book from 2002 is really good starting point for understanding bio-physical models of neuron. It the past it was possible to find this book also in html ..
另一方面,在计算机科学背景下通过尖峰神经元"通常是指 SRMo 模型(Spike Response Model),它可以是也用作基于感知器的经典网络的替代品.
On the other hand by ¨Spiking neuron" in the computer science context is usually meant the SRMo model (Spike Response Model), which can be used also as an alternative to classical percepron-based networks.
这个模型在 Wolfgang Maass 的作品中得到了很好的描述(http://www.igi.tugraz.at/maass/).他专注于计算模型的力量,他将 SRM 模型与 percepron 和RBF-单位.
This model is described very well in the works of Wolfgang Maass (http://www.igi.tugraz.at/maass/). He has focused on the computational power of the model and he compares the SRM model with percepron and RBF-unit.
如果您想在网络中使用该模型,我向您推荐以下作品派生 SpikeProp 的 Sander Bohte (http://homepages.cwi.nl/~sbohte/)算法.
If you want to use the model in a network I recommend to you works of Sander Bohte (http://homepages.cwi.nl/~sbohte/) who derived SpikeProp algorithm.
(我个人衍生出了 SpikeProp 的一个变体,它足够快用于实际应用程序.)"
(I personally derived a variant of SpikeProp which was fast enough to be used for real-word applications.) "
推荐答案
尖峰神经网络 (SNN) 或脉冲神经网络 (PNN) 是人工神经网络 (ANN),可以更密切地模拟自然神经机制的行为.我想建议您阅读以下基础书籍:
Spiking Neural Networks (SNNs) or Pulsed Neural Networks (PNNs) are artificial neural networks (ANNs) that more closely emulate the behaviours of natural neural mechanisms. I would like to advise you following fundamental books:
- Thomas Trappenberg 的计算神经科学基础
- 理论神经科学:神经系统的计算和数学建模作者:Peter Dayan
- 尖峰神经元模型:Wulfram Gerstner 的单神经元、种群、可塑性
我个人衍生了一个远程监督方法(ReSuMe)的变体,与 Filip Ponulak 引入的 ReSuMe 相比,它具有更好的学习率和形态优势.
I personally derived a variant of Remote Supervised Method (ReSuMe) which has better learning rate and morphological advantages compared to ReSuMe introduced by Filip Ponulak.
同时,我想列出一些处理 SNN 的模拟器工具.我玩过的大多数都是基于 Python 的,所以也请考虑到这一点.可能还有更多基于其他语言的其他语言.
In the meantime, I would like to list some of simulator tools dealing with SNNs. Most of them which I played with are based on Python so please take into account that as well. There might be more others based on other languages.
- 无政府状态
- Brian2
- 能歌
- 大象
- 神经元
- PyNN
- NEST/pynest
- PCSIM
- Pypcsim
- BindsNet
这篇关于尖峰神经网络的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!