1.help nndatasets //neural network data sets
2. If even more accurate results were
required, you could try any of these approaches:
• Reset the initial network weights and biases to new values with init and train
again (see “Initializing Weights” (init)).
• Increase the number of hidden neurons.
• Increase the number of training vectors.
• Increase the number of input values, if more relevant information is available
Try a different training algorithm (see “Training Algorithms”).
3.数据被自动分成training set、validation set 及test set 三部分,training set是训练样本数据,validation set是验证样本数据,test set是测试样本数据,这样这三个数据集是没有重叠的。在训练时,用training训练,每训练一次,系统自动会将validation set中的样本数据输入神经网络进行验证,在validation set输入后会得出一个误差(不是网络的训练误差,而是验证样本数据输入后得到的输出误差,可能是均方误差),而此前对validation set会设置一个步数,比如默认是6echo,则系统判断这个误差是否在连续6次检验后不下降,如果不下降或者甚至上升,说明training set训练的误差已经不再减小,没有更好的效果了,这时再训练就没必要了,就停止训练,不然可能陷入过学习。
4.About Overfitting
关于过度拟合的链接
08-21
08-21
08-21
08-21
08-21