McGuire next plans to train the network to process different textures.
McGuire的下一个计划是通过训练神经网络使之能够识别不同的纹理。
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。
应用推荐