Supervised learning with decision margins in pools of spiking neurons.

Supervised learning with decision margins in pools of spiking neurons.
复制标题

DOI:
10.1007/s10827-014-0505-9
复制
发表时间:
2014-10
影响因子:
1.2
通讯作者:
Yger, Pierre
Yger, Pierre
中科院分区:
医学4区
文献类型:
--
作者:
Le Mouel, Charlotte;Harris, Kenneth D.;Yger, Pierre

文献摘要

参考文献

相似文献

通过从几个类别精确已知的例子中归纳,学习对感觉输入进行分类,这是大脑产生适当行为反应的关键一步。在神经元水平上,这可以通过在训练信号的影响下调整突触权重来实现,以便对冲击神经元的尖峰模式进行分组。在这里,我们描述了一个框架,允许尖峰神经元执行这种“监督学习”,使用类似于支持向量机的原理,一个完善的鲁棒分类器。使用铰链损失误差函数,我们表明请求与支持向量机相似的裕度可以提高线性不可分问题的性能。此外,我们还表明,使用神经元池来区分类别也可以通过在神经元之间分担负载来提高性能。本文的在线版本(doi:10.1007/s10827-014-0505-9)包含补充材料,仅供授权用户使用。
Learning to categorise sensory inputs by generalising from a few examples whose category is precisely known is a crucial step for the brain to produce appropriate behavioural responses. At the neuronal level, this may be performed by adaptation of synaptic weights under the influence of a training signal, in order to group spiking patterns impinging on the neuron. Here we describe a framework that allows spiking neurons to perform such “supervised learning”, using principles similar to the Support Vector Machine, a well-established and robust classifier. Using a hinge-loss error function, we show that requesting a margin similar to that of the SVM improves performance on linearly non-separable problems. Moreover, we show that using pools of neurons to discriminate categories can also increase the performance by sharing the load among neurons. The online version of this article (doi:10.1007/s10827-014-0505-9) contains supplementary material, which is available to authorized users.
DOI: 10.1126/science.272.5265.1126
发表时间: 1996-05-24
期刊: SCIENCE
影响因子: 56.9
作者:
Raymond, JL;Lisberger, SG;Mauk, MD
通讯作者: Mauk, MD
DOI: 10.1038/nn.2479
发表时间: 2010-03-01
影响因子: 25
作者:
Clopath, Claudia;Buesing, Lars;Gerstner, Wulfram
通讯作者: Gerstner, Wulfram
DOI: 10.1523/jneurosci.2496-11.2012
发表时间: 2012-01-04
影响因子: 5.3
作者:
El Boustani, Sami;Yger, Pierre;Destexhe, Alain
通讯作者: Destexhe, Alain
DOI: 10.1371/journal.pbio.1000141
发表时间: 2009-07
期刊: PLoS biology
影响因子: 9.8
作者:
Gütig R;Sompolinsky H
通讯作者: Sompolinsky H
DOI: 10.1007/bf00994018
发表时间: 1995-09-01
期刊: MACHINE LEARNING
影响因子: 7.5
作者:
CORTES, C;VAPNIK, V
通讯作者: VAPNIK, V