计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (19): 172-174.
• 图形、图像、模式识别 • 上一篇 下一篇
裴承丹
收稿日期:
修回日期:
出版日期:
发布日期:
通讯作者:
PEI Cheng-dan
Received:
Revised:
Online:
Published:
Contact:
摘要： 循环神经网络（RNN，也称反馈神经网络）是一种重要的人工神经网络，与前馈神经网络相比具有更好的学习能力和更快的收敛速度，但其隐层结构的设计一直是个难点问题。回声状态网络（ESN）有效地解决了上述问题，相比于以前的循环神经网络，其具有结构独特、稳定性好、学习过程简单快捷等特点。介绍了回声状态网络及其学习方法，将其用于图像的边缘检测中，取得了良好的效果。
关键词: 回声状态网络, 边界检测, 统计向量
Abstract: Recurrent Neural Networks（RNN） is a kind of important artificial neural networks with better ability for learning and rate of convergence in comparison with forward neural networks，however，the design of the structure of the hidden-layer is a difficult problem all the time.Echo State Networks has no such problems with special construction，good stability，short-cut learning process.Application of ESN to the edge detection of images has been introduced after the presentation of the structure and method of learning of ESN，resulting well.
Key words: Echo State Networks（ESN）, edge detection, statistical vector
裴承丹. 回声状态网络及其在图像边缘检测中的应用[J]. 计算机工程与应用, 2008, 44(19): 172-174.
PEI Cheng-dan. Echo state networks and its application on image edge detection[J]. Computer Engineering and Applications, 2008, 44(19): 172-174.
0 / 推荐
导出引用管理器 EndNote|Ris|BibTeX
链接本文: http://cea.ceaj.org/CN/
http://cea.ceaj.org/CN/Y2008/V44/I19/172
