| 1. | A method for ica for complex - valued sources
一种针对复值信号的独立分量分析方法 |
| 2. | A novel algorithm is proposed for training complex - valued neural networks
摘要提出了一种新型复数前馈神经网络的学习算法。 |
| 3. | Based on the second order statistics , an algorithm is proposed to separate mixed complex - value signals online
摘要基于二阶统计量，对在线分离复值混合信号法进行了研究。 |
| 4. | The full - rank matrix is employed to find the complex - valued weights between hidden and output layers by the least mean square algorithm
利用这个满秩矩阵，通过最小平方算法就可以求得隐层和输出层之间的复数权值。 |
| 5. | To improve learning speed , a novel method for properly initializing the parameters ( weights ) of training complex - valued neural networks is proposed
摘要为了改善学习速率，提出了一种确定复数神经网络初始权值的新颖方法。 |
| 6. | Because the initialized weights are optimized , the training accuracy and the learning speed are improved a lot for training complex - valued neural networks
初始权值的优化，使得该算法可以有效地提高复数神经网络的训练速度和计算精度。 |
| 7. | An online algorithm for complex independent component analysis was proposed based on the complex nonlinear functions and the decorrelation of two complex - valued vectors
摘要基于复向量不相关特性和复值非线性函数，提出一种在线复值独立分量分析算法。 |
| 8. | The complex - valued weights between hidden and output layer are updated by solving linear system based on finding the complex - valued weights between input and hidden layer
当输入层和隐层之间的权值计算出来后，就可以通过求解线性方程组得到隐层和输出层之间的权值。 |
| 9. | The main idea is to make full use of the decorrelation of two complex - valued vectors in generating independent components by non linear decorrelation
结合非正则复向量的协方差矩阵和伪协方差矩阵构造出了新的代价函数，进而提出新算法，通过复非线性不相关，从混合信号中提取出复值独立分量。 |
| 10. | The gabor transform is one of the most important schemes for time - frequency analysis . since the traditional gabor transform is complex - valued , it ' s real - time applications were limited due to the high complexity involved in the computation of the complex - valued transform
Gabor变换是重要的时频分析方法之一，由于传统gabor变换为复值变换，计算复杂度高、计算量大，限制了gabor变换的实时应用。 |
