为提高并行网络模拟的可用性与运行效率,需要研究有效的拓扑划分方法。
To improve the usability and running efficiency of the parallel network simulation, effective topology partitioning method is required.
通过构造一个特殊的多层前向神经网络,利用模拟并行测量装置的基本原理,设计了相应的谐波监测电路。
Using the basic principle of analog parallel harmonics measurement and a special multi-layer feedforward neural network, a corresponding harmonics measurement on-line is built.
神经网络计算机能模拟人脑的并行处理方式,具有惊人的自学习、思维、推理、判断和记忆的功能。
Neutral network computer can simulate human brains in parallel information processing manner, with functions of striking self-learning, thinking, reasoning, judging, and memorizing.
应用推荐