weight n. 1.重量;体重;求心力,重力,(地心)引力。 2.斤两,分量,衡,计重单位。 3.(压东西的)重物。 4.砝码,秤锤,秤砣。 5.重担,重压;负担,重任。 6.重要性;影响力,势力。 7.【统计】权,加重值,权重,重要度。 8.(合于季节的衣料的)重量,厚薄。 9.拉弓所需的力。 10.【赛马】马应负载的重量〔包括马鞍、骑师等〕。 11.(拳师、摔跤手等的)体重级别。 a paper weight 镇纸。 a pound weight 一磅重的秤砣[砝码]。 a man of weight 重要人物,有势力的人。 a suit of summer weight 夏服一套。 by weight 论重量(卖等)。 carry great [no] weight 极[不]重要,极受[不受]重视。 gain [lose] weight 体重增加[减少]。 give short weight 骗秤头,克扣斤两。 have weight with (sb.) 对(某人)有影响。 pull one's weight 尽自己的本分〔见 pull 条〕 put on weight 体重增加,发胖。 throw one's weight about 大摆架子;作威作福,仗势欺人。 under the weight of 在…的重压下,迫于…。 weight empty 空重,皮重;空载。 weights and measures 度量衡。 vt. 1.在…上加重量,把重量放在…上。 2.使负担,装载;使负重担,装载过重;折磨,压迫。 3.在(织品、丝等内)搀重晶石(等)以增加分量。 4.【统计】使加权,附加加重值于。 5.视…为重要,强调。 weighted with 因…加重;因…烦恼。 adj. -less 无重的;失重的。 n. -lessness 失重。
Application of k - l transformation the optimization of initial weights of bp neural network 网络初始权值优化中的应用
Nntcs employs genetic algorithm ( ga ) in the stage of training to optimize initial weights of ann 训练过程中结合遗传算法,优化神经网络的初始权值。
Genetic algorithm is used to optimize the initial weight of back propagation network and the operation efficiency is enhanced 用遗传算法优化bp网络的初始权值,提高神经网络的运算速度。
The initial weights of the neural network can be given according to the material meaning , which expedites the network convergence 文中将神经网络与ip控制器结合,权的初始值可据其意义设定,大大加快了网络的收敛速度。
In the control process uses two bp network . one is used as nni recognizing the model , another as neural network control device ( nnc ) . but first off - line recognizes controlled device , make sure nnc initial weights 在控制的过程中,采用两个bp网络,一个作为神经网络辨识器( nni )进行辨识建模;另一个作为神经网络控制器( nnc ) 。
The algorithms for training weights update and constructing the target vectors are discussed . use the penalty term to improve the astringency of network . and study how choice the appropriate initial weights 着重研究了根据输入和输出量合理选择网络结构,训练权值的更新算法,目标向量的合理构造,带惩罚项的bp网络,改善了网络的收敛性。
The dependences in multitemporal multispectral images by independent component analysis are reduced . in the algorithm , damped factor is imported to reduce the dependence on initial weights , thus the robust of the algorithm is improved 在改进的独立成分学习算法中,通过在梯度下降方法中引入阻尼因子,降低了对初始值的依赖,提高了独立成分求解的稳健性。
During the course of develop fault diagnostic method , the influence to the training circle number with network structure 、 learning rate 、 initial weight value & door value etc are discussed . by comprehensive analyses and comparing , the comparatively rational value is adopted to be network ' s eigenvalue 在制粉系统故障诊断样本训练过程中,本文作者探讨了网络结构、学习率、初始权值阈值等因素对训练速度的影响,为选取合理的网络参数提供了依据。