Construction of a routing optimization algorithm

提出了一种新的优化算法，并进行了基础实验。研究结果归纳为四篇论文。提出了一种适用于互连接神经网络（MCNN）的涌现学习算法。涌现学习算法使用三种类型的评估值，即节点评估值、链路评估值和整个网络评估值。实验结果表明，MCNN通过突现学习算法获得了最优的网络结构。

A new optimization algorithm was proposed and the basic experiment was conducted. The result of research was summarized as four papers. We proposed the Emergent Learning Algorithm that is applied for Mutually Connected Neural Network(MCNN). The Emergent Learning Algorithm uses three types of evaluation value that are node evaluation, link evaluation and whole network evaluation. The experimental results show that the MCNN obtains optimal network structure by Emergent Learning Algorithm.