Layered Cascade Multi  Subnet Neural Networks

Sun Gongxing; Zhu Kejun; Dai Changjiang; Dai Guiliang

您当前的位置：

首页 >

文章列表页 >

Layered Cascade Multi Subnet Neural Networks

更新时间：2025-12-08

- Layered Cascade Multi Subnet Neural Networks
- Acta Electronica Sinica Issue 8, (1999)
- 作者机构：
  
  中国科学院高能物理研究所
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP18
- Published：1999
- 稿件说明：
移动端阅览
[1]孙功星,朱科军,戴长江,戴贵亮.层次式多子网级联神经网络[J].电子学报,1999(08):50-52.

Sun Gongxing, Zhu Kejun, Dai Changjiang, et al. Layered Cascade Multi Subnet Neural Networks[J]. Acta Electronica Sinica, 1999, (8).
[1]孙功星,朱科军,戴长江,戴贵亮.层次式多子网级联神经网络[J].电子学报,1999(08):50-52. DOI：

Sun Gongxing, Zhu Kejun, Dai Changjiang, et al. Layered Cascade Multi Subnet Neural Networks[J]. Acta Electronica Sinica, 1999, (8). DOI：

摘要

本文提出的层次式多子网级联神经网络是一个新的神经网络自结构方案，它通过不断地加入新的子网，逐一地分解复杂的任务为多个简单的子任务，每个子任务为一专有的子网所处理，从而达到分而治之的目的，使问题得以求解．它的优势性能在于它实现了复杂任务的自动分解和模块化训练策略，降低了全局最优搜索的复杂性，提高了训练速度，改善了网络性能．从模拟结果看，层次式多子网级联神经网络不仅在性能上优于ＢＰ网络，而且，在网络的泛化能力方面也优于级联相关学习网络．

Abstract

A new constructive learning algorithm is proposed in this paper.By allowing to add one subnet each time to existing network during the course of training

it can automatically divide a complex task into a series of subtasks which are processed by their corresponding subnets.The divide and conquer strategy can arrive at a solution to a given task.Its strength lies in its automatic decompostion of given task and its modular training of network.Each of them leads to a great reduction of optimal search effort and an improved training.The simulation result shows that it not only achieves a better perfomance than BP network on two spiral classification problem

but also achieves a better perfomance than Cascade Correlation Learning Network in generalization ability.

关键词

Keywords

references

Views

167

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Real-Time Gesture Recognition Algorithm Based on LoRa Signals

Continual Learning Methods and Applications in Computer Vision

End-to-End Full Complex-Valued Domain SAR Target Classification Neural Network

Related Author

HAN Chong

DU Hao

GUO Jian

SUN Li-juan

FANG Yan

Wei Yun-chao

Cong Run-min

Zuo Wang-meng

Related Institution

College of Computer, Nanjing University of Posts and Telecommunications

Jiangsu Key Laboratory of Intelligent Sensing and Computing for Internet of Things

School of Computer Science and Technology, Beijing Jiaotong University

School of Control Science and Engineering, Shandong University

School of Computer Science and Technology, Harbin Institute of Technology

⁰