今天在阅读tensorflow keras 教程中,学习到以下结论:
Conclusions
To recap: here are the most common ways to prevent overfitting in neural networks:
- Get more training data.
- Reduce the capacity of the network.
- Add weight regularization.
- Add dropout.
Two important approaches not covered in this guide are:
- data-augmentation
- batch normalization
Remember that each method can help on its own, but often combining them can be even more effective.
译文如下:
在神经网络训练中,最常见的防止过拟合的方法有:
1. 获取更多的训练集
2. 减少网络的容量;
3. 增加权重正则化;
4. 减少中间层的输出
另外,还有两种方法也有效,分别是:
5. 数据扩充;
6. 批次标准化
我们需要记住:每一种方法只能对自己有帮助,通常需要把以上方法结合使用,效果更佳。