Such as: existing partial minimum, the slow convergence, selecting the number of hidden nodes difficult and so on.
如:训练时易陷入局部极小、收敛速度慢、隐结点个数难以确定等。
Traditional neural network algorithms are easy to fall into the local minimum, slow convergence when in fault diagnosis.
传统的神经网络算法应用于故障诊断时,具有易陷入局部极小值,收敛速度较慢等缺点。
Reinforcement learning is an important machine learning method. However, slow convergence has been one of main problem in practice.
强化学习是一种重要的机器学习方法,然而在实际应用中,收敛速度缓慢是其主要不足之一。
应用推荐