| 摘要: |
| 本文根据多目标优化理论、认知科学和神经科学等学科的最新成果，提出了一种基于多目标优化的神经网络快速学习算法．实验结果表明，该学习算法可以解决目前神经网络普遍存在的学习时间长、容易陷入局部极小和网络结构优化难等问题. |
| 关键词: 神经网络 多目标优化 学习算法 网络优化 认知科学 |
| DOI： |
| 分类号: |
| 基金项目:本文研究得到国家自然科学基金资助. |
|
| A FAST NEW NEURAL NETWORK LEARNING ALGORITHM BASED ON MULTIOBJECTIVE OPTIMIZATION |
|
Wang Jicheng,Lu Weixue
|
| Abstract: |
| In this paper, a fast new neural network learning algorithm based on multiobjective optimization is presented according to the new research results of multiobjectiveoptimization, cognitive science and neurology. The experiment results have shown thatthis algorithm can solve the problems of long learning time, local minima and difficult network optimization. |
| Key words: Neural network multiobjective optimization learning algorithm networkoptimization cognitive science. |
