Artificial Neural Networks and Machine Learning - ICANN 2012
Artificial Neural Networks and Machine Learning - ICANN 2012
复制标题
人工神经网络和机器学习 - ICANN 2012
DOI：
10.1007/978-3-642-33269-2_34
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Sporea I
中科院分区：
文献类型：
--
作者：
Sporea I
在本文中，使用具有附加和缺失尖峰的尖峰序列模式来测试前馈尖峰神经网络。该网络使用噪声和扭曲模式进行训练，并将 ReSuMe 学习规则扩展到具有隐藏层的网络。结果表明，多层 ReSuMe 可以可靠地学习区分跨度超过 500 ms 的高度扭曲模式。
In this paper, a feed forward spiking neural network is tested with spike train patterns with additional and missing spikes. The network is trained with noisy and distorted patterns with an extension of the ReSuMe learning rule to networks with hidden layers. The results show that the multilayer ReSuMe can reliably learn to discriminate highly distorted patterns spanning over 500 ms.