欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为了模仿人脑的复杂功能,把各种相关类型的神经网络组织起来,形成一个大规模混合神经网络。根据此需求,使用自主研发的LabGrid技术开发了一个基于网格的混合神经网络计算平台,利用该平台设计了一种新的混合神经网络分类系统来对该平台进行测试。测试结果表明,该平台具有较高的效率和良好的容错性。与其它分类系统比较可知,该分类系统有较高的准确率,从而证明了模仿人脑建立大规模混合神经网络分类系统的可行性和有效性。
英文摘要：
In order to imitate the complex function of a brain,it is necessary to combine different kinds of neural networks to form a large-scale of hybrid neural network.According to this requirement,the LabGrid technique is used to develop the grid-based computing platform for the hybrid neural network,and a new hybrid neural network classifier system is designed to test the platform.The experi-mental results show that the platform is efficiency and fault-tolerant.And compared with other classifier system,the new classifier system has higher ratio of correct classification,which proves that it is feasible and effective to build a large-scale of hybrid neural network for imitating the brain.
同期刊论文项目
同项目期刊论文
位置：