首页> 外国专利> DISTRIBUTED CELLULAR COMPUTING SYSTEM AND METHOD FOR NEURAL-BASED SELF-ORGANIZING MAPS

DISTRIBUTED CELLULAR COMPUTING SYSTEM AND METHOD FOR NEURAL-BASED SELF-ORGANIZING MAPS

机译:分布式蜂窝计算系统和基于神经的自组织地图的方法

摘要

The present invention provides a neuromorphic computing system configured to be trained using unsupervised learning through distributed computing means. The neuromorphic computing system comprises a Self-Organizing Map (SOM) implemented in a grid organized as a plurality of locally connected cells wherein each cell comprises neuron computing means to perform neuron computations. The neuromorphic computing system is characterized in that the neuron computing means are configured to allow at each active edge of a clock system that each cell of the grid performs neuron computations on an input data and propagates the result of its neuron computation to its connected neighbors at the next active clock edge, thereby an input data being iteratively propagated to all cells of the grid.Advantageously, the iterative method of the present invention brings a formalized, validated, generic and hardware-efficient solution to the scalability problem of centralized and fully-connected distributed SOMs implementations.
机译:本发明提供了一种神经形态计算系统,其配置为通过分布计算装置使用无监督学习进行训练。神经形态计算系统包括以组织为多个局部连接的小区的网格中实现的自组织地图(SOM),其中每个单元包括神经元计算装置以执行神经元计算。神经形态计算系统的特征在于,神经元计算装置被配置为允许在时钟系统的每个主动边缘处,该网格的每个单元在输入数据上执行神经元计算,并将其神经元计算结果传播到其连接的邻居下一个有源时钟边缘,从而迭代地传播到网格的所有单元的输入数据。方便地,本发明的迭代方法为集中式和完全的可扩展性问题带来了正式的,验证,通用和硬件有效的解决方案连接分布式SOMS实现。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

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