Based on the idea of data parallelism, a parallel training model for RBF (radial basis function) neural network in time-series prediction to improve the training speed is proposed.
根据数据并行的思想，提出了在时序预测中并行训练神经网络的模型，以提高训练速度。
To solve the problems above, this paper brings forward the solutions as follows: Ameliorating the capability of computer-based translation by better employment of existing parallel training corpus.
针对以上问题，本文提出以下方法：通过更好地利用现有平行训练语料去改善统计计算机翻译的性能。
This paper applies parallel tangents of nonlinear programming during the weights training of neural network and puts forward a neural network in view of fast learning algorithm.
因此，作者将非线性规划的平行切线算法用于神经网络的权值学习，提出了一种具有快速学习算法的神经网络。
In this paper, a balance training system based on parallel robot is designed to train the dynamic balance ability.
本文设计的基于并联机器人的平衡训练系统主要用于动态平衡能力的训练。
Firstly, sample set is roughly classified using ART to reduce the scale of samples, in training set, and then all small training sets is trained using parallel BP.
首先用ART网络对训练集中的样本进行粗分类，以减小训练集的样本规模，然后用多个BP网络并行地对小训练集进行训练。
Explores the training problems of support vector machine with large training pattern set, and a new parallel algorithm based on orthogonal array is presented.
对大规模训练样本的支持向量机训练问题进行探索，提出了一种基于正交表的并行学习算法。
The improved GFMM neural network possessed the full capability of unsupervised training and self-adapting adjustment, which showed the good ability of parallel disposal.
改进后的GFMM神经网络完全具备了自适应调整和无师学习的能力，并展现出了良好的并行处理性能。
A parallel implementation of the algorithm using standard MPI communication routines is provided to handle large-scale problems and to accelerate the training process.
提供的算法的并行执行使用标准MPI通讯例程来处理大规模的问题，并加快培养过程。
With such strength training can be supported on the parallel bars.
等有了力量可以在双杠上练支撑。
Thirdly, a GPU based massively data parallel C-SVM classification (GMP-CSVC) algorithm is presented to reduce the training time of SVM.
第三，针对支持向量机算法复杂度较高，难以应用于大样本分类的问题，提出了GMP-CSVC算法。
Thirdly, a GPU based massively data parallel C-SVM classification (GMP-CSVC) algorithm is presented to reduce the training time of SVM.
第三，针对支持向量机算法复杂度较高，难以应用于大样本分类的问题，提出了GMP-CSVC算法。
应用推荐