论文部分内容阅读
探讨了多层前向神经网络的学习算法，并将该算法用于大型聚酯生产工况预测。结合非线性最优化方法，提出了一种基于拟牛顿法的神经元网络自调节变尺度学习算法，仿真结果表明，该算法有效地改进了神经元网络学习收敛速度和收敛性能。
The learning algorithm of multi-layer forward neural network is discussed and the algorithm is applied to the prediction of large-scale polyester production. Based on the quasi-Newton method, a self-adjusting and scaled learning algorithm based on quasi-Newton method is proposed. The simulation results show that this algorithm can effectively improve the convergence speed and convergence performance of neural network learning.