Neural Network Integration can significantly improve the generalization ability of leaning systems through training a finite number of neural network and they combining their results.
这种方法通过多个神经网络的集成来协同识别产品故障分布，所以它较之单个神经网络有更强的推广能力、更容易训练。
Financial time series has high randomicity and nonlinearity. Neural network is quite suitable in the process of financial time series data for its good ability of nonlinear mapping and generalization.
金融时间序列具有很强的随机性和非线性性，而神经网络具有良好的非线性映射能力及自适应、自学习和良好的泛化能力，因此非常适合处理金融时间序列这样的数据。
The BP neural network is adopted to realize the reinforcement learning to strengthen the generalization ability.
应用BP神经网络实现强化学习，以增强系统的泛化能力；
应用推荐