摘要
提出了一种基于最小平均风险准则的遗传算法优化设计前向神经网络的方法,遗传算法的适应度函数并不采用传统的均方误差准则,而是由平均风险准则所决定。这种方法在计算神经网络输出与期望输出之间误差的同时,还要考虑神经网络对不同类型训练样本产生的这种误差所引起的不同的风险损失。这种方法优化得到的神经网络不仅可以准确地再现训练样本集合的期望输出,对训练样本集合外样本的正确预测能力也有明显的提高。
A novel approach for optimizing feed forward neural networks is proposed in this paper, the genetic algorithms is not based on the traditional criterion of minimum square error, however its fitness function is determined by the average risk. In the evolutionaryprocedure, the method considers not only the errors between the network's outputs and the desired outputs, but also the risk caused by these errors, because the errors for different types of samples in training set may present different risks. The neural networks optimized by the proposed approach has shown the good performance on the samples both inside and outside training set. ;;;;
出处
《计算机工程》
CAS
CSCD
北大核心
2002年第7期17-19,共3页
Computer Engineering
基金
江西省跨世纪学科带头人培养计划资助项目第三批
()江西省自然科学基金资助项目()9911013
关键词
最小风险准则
遗传算法
优化
神经网络
均方误差准则
图像识别
计算机
Genetic algorithm Neural networks Optimization Criterion of minimum averaged riskCriterion of square error
