首页> 外文期刊>電子情報通信学会技術研究報告. ニュ-ロコンピュ-ティング. Neurocomputing >Temporal signal processing with a self-organizing map: an application to Braille recognition task
【24h】

Temporal signal processing with a self-organizing map: an application to Braille recognition task

机译:具有自组织地图的时间信号处理:盲文识别任务的应用程序

获取原文
获取原文并翻译 | 示例
           

摘要

An Elman-type feedback SOM is a model which has a feedback loop around the standard SOM's competitive layer, and also has an extra output layer to express quantitative reliability of the applied input signals. In order to investigate its effectiveness, a Braille recognition task is tried with some words containing partially common letters. Because a Braille letter consists of six dots (3×2),it can be seen as spatial/temporal information depending on its width/length direction. As a result, it is found that the model shows good performance appropriately.
机译:ELMAN型反馈SOM是具有围绕标准SOM的竞争层的反馈回路的模型,并且还具有额外的输出层,以表达所施加的输入信号的定量可靠性。 为了调查其有效性,盲文识别任务是用含有部分常见字母的一些单词尝试。 因为盲文信包括六个点(3×2),所以它可以视为空间/时间信息,这取决于其宽度/长度方向。 结果,发现该模型适当显示出良好的性能。

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