...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neurocomputing >Efficient training of supervised spiking neural networks via the normalized perceptron based learning rule
【24h】

Efficient training of supervised spiking neural networks via the normalized perceptron based learning rule

机译：通过基于标准化感知器的学习规则对有监督的尖峰神经网络进行有效的训练

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The spiking neural networks (SNNs) are the third generation of artificial neural networks, which have made great achievements in the field of pattern recognition. However, the existing supervised training methods of SNNs are not efficient enough to meet the real-time requirement in most cases. To address this issue, the normalized perceptron based learning rule (NPBLR) is proposed in this paper for the supervised training of the multi-layer SNNs. Different from traditional methods, our algorithm only trains the selected misclassified time points and the target ones, employing the perceptron based neuron. Furthermore, the weight modification in our algorithm is normalized by a voltage based function, which is more efficient than the traditional time based method because the firing time is calculated by the voltage value. Superior to the traditional multi-layer algorithm ignoring the time accumulation of spikes, our algorithm defines the spiking activity of the postsynaptic neuron as the rate accumulation function of all presynaptic neurons in a specific time-frame. By these strategies, our algorithm overcomes some difficulties in the training of SNNs, e.g., the inefficient and no-fire problems. Comprehensive simulations are conducted both in single and multi-layer networks to investigate the learning performance of our algorithm, whose results demonstrate that our algorithm possesses higher learning efficiency and stronger parameter robustness than traditional algorithms. (C) 2017 Elsevier B.V. All rights reserved.
机译：尖峰神经网络（SNN）是第三代人工神经网络，在模式识别领域取得了巨大成就。然而，在大多数情况下，现有的SNN监督训练方法不够高效，无法满足实时需求。为了解决这个问题，本文提出了基于标准化感知器的学习规则（NPBLR），用于多层SNN的监督训练。与传统方法不同，我们的算法仅使用基于感知器的神经元训练选定的错误分类时间点和目标时间点。此外，我们算法中的权重修改是通过基于电压的函数进行归一化的，这比传统的基于时间的方法更有效，因为触发时间是通过电压值来计算的。优于传统的多层算法，它忽略了尖峰的时间累积，我们的算法将突触后神经元的突波活动定义为特定时间范围内所有突触前神经元的速率累积函数。通过这些策略，我们的算法克服了SNN训练中的一些困难，例如效率低下和不点火的问题。在单层和多层网络中均进行了全面的仿真，以研究该算法的学习性能，其结果表明，与传统算法相比，该算法具有更高的学习效率和更强的参数鲁棒性。 （C）2017 Elsevier B.V.保留所有权利。

著录项

  • 来源
    《Neurocomputing》 |2017年第7期|152-163|共12页
  • 作者

    Xie Xiurui; Qu Hong; Liu Guisong; Zhang Malu;

  • 作者单位

    Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu 610054, Peoples R China;

    Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu 610054, Peoples R China;

    Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu 610054, Peoples R China;

    Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu 610054, Peoples R China;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Spiking neural networks; Temporal encoding mechanism; Supervised learning; Perceptron based learning rule;

    机译：尖刺神经网络;时间编码机制;监督学习;基于感知器的学习规则;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号