1) Self-organized Competitive Neural Network(SCNN)
自组织竞争人工神经网络
1.
Because Back-propagation Neural Network(BPN) has the shortcomings of bad convergence and low efficiency,and Self-organized Competitive Neural Network(SCNN) can overcome these shortcomings.
提出了将自组织竞争人工神经网络(SCNN)和小波矩结合进行图像旋转不变识别的新方法。
2) Self-organizing NNs
自组织竞争型人工神经网络
1.
The paper uses Self-organizing NNs as tools to cluster the level of present transportation-development of all the provinces in our country.
通过直截利用人工神经网络中的工具箱函数 ,进行编程 ,能迅速得到正确、简明的结果 ,说明了自组织竞争型人工神经网络用于解决分类问题的正确
3) self-organizing competitive neural network
自组织竞争神经网络
1.
On the basis of the artificial neural networks(ANN),a self-organizing competitive neural network model was developed and used for automation recognition of dynamometer cards and fault diagnosis for suck rod pumping system.
5进行编程,应用相同的数据对BP神经网络模型和自组织竞争神经网络模型的识别效率进行了对比。
2.
Then,a two-layer self-organizing competitive neural network was built.
从ECT传感器的输出中提取特征参数作为软测量模型的辅助变量,两相流流型为主导变量,构建二级自组织竞争神经网络,进而实现对两相流流型的在线判别。
3.
Twenty-one absorption peak data from the first three principal componment compressed from the original data by PLS were taken as inputs of the self-organizing competitive neural network.
用PLS法对原始数据进行主成分压缩,采用自组织竞争神经网络建模。
4) self-organization competitive neural network
自组织竞争网络神经网络
6) self-organizing competitive network
自组织竞争网络
1.
Based on the theory of self-organizing competitive network,the present paper discusses the appraisal system of basketball teaching.
运用自组织竞争网络理论与方法,通过教学实验初步构建高等院校体育专业篮球教学评价体系。
2.
The effect of samples training on BP neural network performance with the clustering characteristic of self-organizing competitive network is improved.
通过自组织竞争网络的聚类特征,改善样本训练对BP网络性能的影响。
补充资料：人工神经网络
| 人工神经网络 artificial neural network 一种模仿动物神经网络行为特征的分布式并行信息处理算法结构的动力学模型。它用接受多路输入刺激，按加权求和超过一定阈值时产生“兴奋”输出的部件来模仿动物神经元的工作方式，并通过这些神经元部件相互联接的结构和反映关联强度的权系数使其“集体行为”具有各种复杂的信息处理功能。特别是这种宏观上具有鲁棒、容错、抗干扰、适应性、自学习等灵活而强有力功能的形成不是由于元部件性能不断改进，而是通过复杂的互联关系得以实现，因而人工神经网络是一种联接机制模型，具有复杂系统的许多重要特征。人工神经网络适用于信号处理、数据压缩、模式识别 、机器人视觉、知识处理及其应用，预测、评价和决策问题 ，调度排序、路由规划等组合优化问题。在控制系统设计中它可用于模拟被控对象特性、搜索和学习控制规律、实现模糊和智能控制。 |
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条