An extension of multi-layer perceptron based on layer-topology

被引：0

作者：

Zuters, J ^{[1
]}

机构：

[1] Latvian State Univ, Dept Comp Sci, LV-1063 Riga, Latvia

来源：

ENFORMATIKA, VOL 7: IEC 2005 PROCEEDINGS | 2005年

关键词：

learning algorithm; multi-layer perceptron; topology;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

There are a lot of extensions made to the classic model of multi-layer perceptron (MLP). A notable amount of them has been designed to hasten the learning process without considering the quality of generalization. The paper proposes a new MLP extension based on exploiting topology of the input layer of the network. Experimental results show the extended model to improve upon generalization capability in certain cases. The new model requires additional computational resources to compare to the classic model, nevertheless the loss in efficiency isn't regarded to be significant.

引用

页码：178 / 181

页数：4