| 多层前馈神经网络的学习和综合算法 |
| |
| 引用本文： | 张铃,吴福朝,张钹,韩玫.多层前馈神经网络的学习和综合算法[J].软件学报,1995,6(7):440-448. |
| |
| 作者姓名： | 张铃 吴福朝 张钹 韩玫 |
| |
| 作者单位： | 安徽大学人工智能所,合肥，230039;安徽大学人工智能所,合肥，230039;清华大学计算机系,北京,100084;清华大学计算机系,北京,100084 |
| |
| 基金项目： | 本项目得到攀登计划和863高技术计划的资助. |
| |
| 摘 要： | 本文提出多层前馈网络的一种新的学习和综合算法──ＦＰ算法，并证明由此算法得到的网络作为通用联想记忆器时，具有如下优点：（１）每个样本都是吸引中心；（２）每个样本的吸引半径达到最大值；（３）网络没有假吸引中心；（４）网络具有最少的元件个数；（５）学习的复杂性达到最优（就其复杂性的阶而言）．故此网络在性能、结构、计算复杂性等方面均达到很好状态．
|
| 关 键 词： | 地图 颜色 分层 聚类 识别 |
| 收稿时间： | 1994/2/25 0:00:00 |
| 修稿时间： | 1994/8/22 0:00:00 |
AN ALGORITHM FOR LAYERING MAP IMAGE BY COLOUR |
| |
| Zhang Ling,Wu Fuchao,Zhang Bo and Han Mei.AN ALGORITHM FOR LAYERING MAP IMAGE BY COLOUR[J].Journal of Software,1995,6(7):440-448. |
| |
| Authors: | Zhang Ling Wu Fuchao Zhang Bo and Han Mei |
| |
| Abstract: | A new learning algorithm-forward propagation (FP) of multilayered feed-forward neural networks is presented in this paper. The authors show that as an associative memory the network constructed by the FP algorithm has several advantages. (1)Each training sample is an attractive center. (2) The attractive radius of each training sample reaches the maximum. (3) There is no spurious attractive center in the network.(4) The network has minimal number of elements. (5) The order of its learning complexity is optimal. The FP learning algorithm is also an effective synthesis tool, i. e., the network architecture can be constructed during its learning process. |
| |
| Keywords: | Map colour layering collection recognition |
| 本文献已被 CNKI 维普 等数据库收录！ |
| 点击此处可从《软件学报》浏览原始摘要信息 |
|
点击此处可从《软件学报》下载全文 |
|
