• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Pattern Recognition >VOWEL: A Local Online Learning Rule for Recurrent Networks of Probabilistic Spiking Winner- Take-All Circuits
【24h】

VOWEL: A Local Online Learning Rule for Recurrent Networks of Probabilistic Spiking Winner- Take-All Circuits

机译：元音：概率尖刺冠军竞赛冠军的经常性网络的当地在线学习规则 - 所有电路

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Networks of spiking neurons and Winner- Take-All spiking circuits (WTA -SNNs) can detect information encoded in spatio-temporal multi-valued events. These are described by the timing of events of interest, e.g., clicks, as well as by categorical numerical values assigned to each event, e.g., like or dislike. Other use cases include object recognition from data collected by neuromorphic cameras, which produce, for each pixel, signed bits at the times of sufficiently large brightness variations. Existing schemes for training WTA -SNNs are limited to rate-encoding solutions, and are hence able to detect only spatial patterns. Developing more general training algorithms for arbitrary WTA -SNNs inherits the challenges of training (binary) Spiking Neural Networks (SNNs). These amount, most notably, to the non-differentiability of threshold functions, to the recurrent behavior of spiking neural models, and to the difficulty of implementing backpropagation in neuromorphic hardware. In this paper, we develop a variational online local training rule for WTA-SNNs, referred to as VOWEL, that leverages only local pre- and post-synaptic information for visible circuits, and an additional common reward signal for hidden circuits. The method is based on probabilistic generalized linear neural models, control variates, and variational regularization. Experimental results on real-world neuromorphic datasets with multi-valued events demonstrate the advantages of WTA-SNNs over conventional binary SNNs trained with state-of-the-art methods, especially in the presence of limited computing resources.
机译：尖峰神经元和获胜者的网络 - 所有尖刺电路（WTA -SNNS）都可以检测在时空多值事件中编码的信息。这些由感兴趣事件的时序描述，例如，点击，以及分配给每个事件的分类数值，例如，例如或不喜欢。其他用例包括由神经形状摄像机收集的数据的对象识别，该数据的用于每个像素在足够大的亮度变化的时间内产生签名位。训练WTA -SNN的现有方案仅限于速率编码解决方案，因此能够仅检测空间模式。为任意WTA -SNNS开发更一般的培训算法继承了训练（二进制）尖峰神经网络（SNNS）的挑战。这些量，最值得注意的是，阈值函数的非差异性，以尖刺神经模型的复发行为，并难以在神经胸壁硬件中实施反向衰减。在本文中，我们开发了用于WTA-SNN的变分在线本地培训规则，称为元音，仅利用可见电路的局部预先和突触后信息，以及隐藏电路的附加常见奖励信号。该方法基于概率概括的线性神经模型，控制变体和变分正则化。具有多价事件的现实世界神经形态数据集的实验结果证明了WTA-SNNS在具有最先进的方法培训的传统二元SNNS上的优点，尤其是在有限的计算资源存在。

著录项

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