The experimental results show that the network learning speed can be increased and the nonlinear errors of the sensors can be reduced by using BPNN.
实验结果表明采用BP神经网络可以提高网络收敛速度,大大减小传感器线性误差。
With the study of neural network model, this paper advances some of improvement and optimization techniques that can accelerate the learning speed of network and increase the stability of model.
本文从神经网络模型的结构出发,对学习算法提出了一系列改进和优化措施,以加快网络的学习速度,并增加模型的稳定性。
The application of additional momentum and adaptive learning rate overcomes the limitation effect of BP rule, accelerates the training speed and strengthens the generalization ability of network.
由于采用附加动量项和自适应率等措施,克服了BP规则的局限性,加快了训练速度,增强了网络的泛化能力。
应用推荐