Considering the limitation of classical BP algorithm, modified BP algorithm is used to train the network.
考虑到经典BP算法的缺陷，采用改进BP算法对网络进行训练学习。
The first order gradient optimization algorithm is employed to train the network. The training samples stem from the neutron kinetics of the point-reactor.
神经网络的训练采用一阶梯度优化算法，利用点堆中子动力学模型产生训练样本。
Moreover, an improved conjugate gradient algorithm is used to train the network and to overcome the shortcoming of easily trapping into local minimum points.
网络训练时采用共轭梯度学习算法并对此算法进行了改进，有效的克服了梯度学习算法容易陷入局部极小的缺点。
The actual data of naval vessel sonar are used to train the network, and then the trained neural network can forecast the naval vessel sonar self-noise accurately.
利用舰艇声呐实测数据进行网络训练，训练好的神经网络可以对舰艇声呐部位自噪声进行精确预报。
Some data were chosen to train the network model. The results show that the convergence rate was faster, the model had higher accuracy, the average absolute error can reach 0.002 7%.
对现场收集的数据进行仿真学习，结果表明，该预测模型收敛速度快，具有较高的预测精度，平均绝对误差可达到0.002 7%。
When BP network model is established, 8 parameters affecting the debris flows activity of the studying area are chose as the net input layer, and 20 samples are used to train the network.
在BP网络模型建立时采用了对研究区泥石流活跃程度影响最主要的8个参数作为输入层，并选取了研究区的20个样本对网络进行训练。
Combined Genetic Algorithms (ga) and back-propagation neural network (BP), an optimized GA-BP model was established to predict phosphorus content. Some data were chosen to train the network model.
结合遗传算法(GA)和误差反馈型神经网络(BP)，建立了优化的GA - BP神经网络预测模型，预测转炉炼钢过程钢液终点磷含量。
Combined Genetic Algorithms (ga) and back-propagation neural network (BP), an optimized GA-BP model was established to predict phosphorus content. Some data were chosen to train the network model.
结合遗传算法(GA)和误差反馈型神经网络(BP)，建立了优化的GA - BP神经网络预测模型，预测转炉炼钢过程钢液终点磷含量。
应用推荐