.png){kind=icon}
返回
Analysis-adjustment-synthesis networks
.png){kind=icon}
OA
AI
DOI：10.1080/09540090701434465.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper presents a novel neural network architecture, analysis-adjustment-synthesis network (AASN), and tests its efficiency and accuracy in modelling non-linear function and classification. The AASN is a composite of three sub-networks: analysis sub-network; adjustment sub-network; and synthesis sub-network. The analysis sub-network is a one-layered network that spreads the input values into a layer of 'spread input neurons'. This synthesis sub-network is a one-layered network that spreads the output values back into a layer of 'spread output neurons'. The adjustment sub-network, between the analysis sub-network and the synthesis sub-network, is a standard multi-layered network that operates as the learning mechanism. After training the adjustment sub-network in recalling phase, the synthesis sub-network receives the output values of spread output neurons and synthesizes them into output values with a weighted-average computation. The weights in the weighted-average computation are deduced from the method of Lagrange multipliers. The approach is tested using four function mapping problems and one classification problem. The results show that combining the analysis sub-network and the synthesis sub-network with a multi-layered network can significantly improve a network's efficiency and accuracy.
Keyword:
spread neuron
function mapping
classification
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。
期刊
IF:
3.4
论文数:
854
被引数:
1.5K
机构
暂无机构信息
引用论文
Evaluating the Vapnik-Chervonenkis dimension of artificial neural networks using the Poincare polynomial.png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏分享收藏Identification and control of dynamic systems using recurrent fuzzy neural networks基于递归模糊神经网络的动态系统辨识与控制
PREAI
分享收藏Probabilistic Impact Assessment of Electric Truck Charging on a Medium Voltage Grid电动卡车充电对中压电网的概率影响评估
PREAI
分享收藏分享收藏A constructive design method for two-layer perceptrons and its application to the design of modular neural networksEXPERT SYSTEMS
EXPERT SYSTEMSIF2.3
PREAI
分享收藏
查看更多内容