首页> 外文会议>5th European symposium on artificial neural networks >An algebra for recognition of spatio-temporal forms
【24h】

An algebra for recognition of spatio-temporal forms

机译:识别时空形式的代数

获取原文
获取原文并翻译 | 示例

摘要

In the new model presented here, post-synaptic potentials are considered as punctual numerical elements on which neurons perform operations. Modelled in this manner, a neural network appears like a calculating machine with an asynchronous internal architecture. To formalize the functioning of such a calculator we propose an algebra of impulses based on the capacities in sequence recognition of a neuron (W. Rail's biological model). The aimed applicative domain is the realisation of perceptive systems which exploit signal dynamics.
机译:在此处介绍的新模型中,突触后电位被视为神经元对其执行操作的守时数值元素。以这种方式进行建模,神经网络看起来就像是具有异步内部体系结构的计算机。为了使这种计算器的功能正式化,我们基于神经元的序列识别能力(W. Rail的生物学模型)提出了脉冲的代数。目标应用领域是利用信号动力学的感知系统的实现。

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