Platform Development of Optimization System based on Active Artificial Neural Network

本研究的目的是关于一个基于人工神经网络的实用系统，我们的研究结果如下。利用该网络，我们总能得到一个最优解，这是一个实用的、典型的旅行推销员问题。此外，我们还提出了一种DS-net来缩短计算时间。2)为了应用并行计算算法，我们提出了模块化神经网络，并使用了GPGPU技术，从而大大减少了计算时间。3)我们开发了一个原型支持GUI工具来设计神经网络系统。

The purpose of this research is about a practical system based on Artificial Neural Networks, our results are as follows. To use this network, we can always get a best solution of Travelling Salseman Problem which is a practical and typical one. Moreover, we proposed a DS-net to improve calculation time. 2) To the purpose of applying a parallel computation algorithm, we proposed a modular neural network and we used a GPGPU technique and then we achevied an extensive calculation time reduction. 3) We developed a prototype supportive GUI tool to desinge the neural network system.