• 主题
高级搜索  >
历史搜索 清空历史
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

页面导航
  • 摘要
  • 著录项
  • 相似文献

摘要

A neuromorphic computing system configured to be trained using unsupervised learning through distributed computing means is provided. The neuromorphic computing system includes an artificial neural network implemented as a grid of locally connected cells wherein each cell comprises hardware components for neural computing and storage, and is connected to its direct closest neighbors. The neuromorphic computing system includes a clock system providing periodic active clock edges allowing in each cell to simultaneously and synchronously compute the neuron's Euclidean distance to the input, then compute the Best Matching Unit and the Manhattan distance to it in multiple clock cycles based on a time to Manhattan distance transformation, and finally update the neuron's weights. Advantageously, the iterative method brings a formalized, validated, generic and hardware-efficient solution to the scalability problem of centralized and fully-connected distributed SOMs implementations. The system operates with the same clock frequency regardless of the number of neurons, such that the input rate evolves in square root complexity with respect to the number of neurons in the grid.
机译：提供了一种被配置为通过分布计算装置的无监督学习训练的神经形态计算系统。神经形态计算系统包括作为本地连接电池的网格实现的人工神经网络，其中每个单元包括用于神经计算和存储的硬件组件，并且连接到其直接最接近的邻居。神经形态计算系统包括提供周期性有源时钟边缘的时钟系统，允许每个小区同时且同步地将Neuron的欧几里德距离与输入同步地计算，然后基于时间在多个时钟周期中计算最佳匹配单元和曼哈顿距离。到曼哈顿距离变换，最后更新了神经元的重量。有利地，迭代方法为集中式和完全连接的分布SOMS实现的可扩展性问题带来了形式化的，验证，通用和硬件有效的解决方案。无论神经元数如何，系统以相同的时钟频率运行，使得输入速率相对于网格中的神经元数在方形复杂性中发展。

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