… Considering the structure feature of CPNN, we proposed a new training method based on
particle swarm optimization (PSO). This method utilizes PSO to optimize the structure of CPNN …

… 迭代次数Epoch 训练100 次, 对于输入批次的样本数量的模型学习率Learning-rate 进行了多组
… Comparison of learning rates with training and testing samples 图7. 不同学习率的训练与测试…

Aiming at the problem that it is difficult to determine the modeling factors and the non-linear
runoff prediction modeling in runoff prediction modeling, this paper uses a homogeneous …

Based on the field tunneling data and geological data of deep buried hard rock tunnel boring
machine (TBM) tunnel with a diameter of 7.8 m, a time-series prediction model of TBM …

Predictive models built using temporal data in electronic health records (EHRs) can potentially
play a major role in improving management of diseases. Due to the sequence correlation …

… 为了减少无线传感器网络中的冗余数据量,降低传输能耗,提出一种基于BP神经网络的数据融合
算法(adaptive learning rate back-propagation data fusion algorithm,ALR-BPDFA).该算法首先…

… algorithm share the same learning rate, and the learning rate needs to be set by workers.
Adadelta algorithm has the characteristic of adaptive learning rate, … independent learning rate. …

… To improve the algorithm and accelerate the convergence of training IT-NN, here we …
factor η and adaptive learning rate, rx and rw. Based on original learning algorithm, the input is …

… method and the adaptive learning rate, was used to combine the two methods to form a
dynamic adaptive learning rate BP improved algorithm, which improved the training of the BP …