.png){kind=icon}
.png){kind=icon}
返回
Discrimination networks for maximum selection
.png){kind=icon}
PRE
AI
DOI：10.1016/S0893-6080(03)00205-3.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We construct a novel discrimination network using differentiating units for maximum selection. In contrast to traditional competitive architectures like MAXNET the discrimination network does not only signal the winning unit, but also provides information about its evidence. In particular, we show that a discrimination network converges to a stable state within finite time and derive three characteristics: intensity normalization (P-1), contrast enhancement (P-2), and evidential response (P-3). In order to improve the accuracy of the evidential response we incorporate distributed redundancy into the network. This leads to a system which is not only robust against failure of single units and noisy data, but also enables us to sharpen the focus on the problem given in terms of a more accurate evidential response. The proposed discrimination network can be regarded as a connectionist model for competitive learning by evidence. (C) 2003 Elsevier Ltd. All rights reserved.
Keyword:
competitive learning
contrast enhancement
distributed redundancy
dynamical systems
evidential response
maximum selection
winner-takes-all networks
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。