A hybrid learning approach is presented in which genetic algorithms are used to optimize both the network architecture and the regularization coefficient.
提出了一种利用遗传算法优化前向神经网络的结构和正则项系数的混合学习算法。
This paper presents the concept of knowledge transformation coefficient, learning ability coefficient and knowledge rigidity etc.
本文提出了知识转化系数、学习能力系数和知识刚度等概念，并相应建立了竞争能力的评价模型。
After exploratory researches for the structure and learning algorithm of neural network, an algorithm based on adaptive gain coefficient is presented.
对神经网络的结构和学习算法进行了探索性研究，引入一种基于自适应增益系数改进的学习算法。
Based on this, this paper proposes a hybrid method that simultaneously considers these three factors, and dynamically tunes the learning rate and regularization coefficient.
在此基础上，本文提出了一种混合的方法，同时考虑这三个因素，动态调整学习率和正则化系数。
Finally, the combination forecasting based on meta-learning is introduced which ensure that the weight coefficient between 0 and 1.
最后，引入了基于元学习理论的组合预测，确保权重系数在0到1之间。
The self-adaptive learning rate and momentum coefficient are used to avoid the local minimum point in the training process of wavelet neural network.
小波神经网络的训练采用自适应调整学习率及动量系数的方法，以避免陷入局部极小值。
The self-adaptive learning rate and momentum coefficient are used to avoid the local minimum point in the training process of wavelet neural network.
小波神经网络的训练采用自适应调整学习率及动量系数的方法，以避免陷入局部极小值。
应用推荐