Applied Deep Learning: A Case-Based Approach to Understanding Deep Neural Networks

© Umberto Michelucci 2018

Umberto MichelucciApplied Deep Learninghttps://doi.org/10.1007/978-1-4842-3790-8_5

5. Regularization

Umberto Michelucci¹ 

(1)

toelt.ai, Dübendorf, Switzerland

 

In this chapter, you will look at a very important technique often used when training deep networks: regularization. You will look at techniques such as the ℓ₂ and ℓ₁ methods, dropout, and early stopping. You will see how these methods help avoid the problem of overfitting and achieve much better results from your models, when applied correctly. You will look at the mathematics behind the methods and at how to implement it in Python and TensorFlow correctly.

Complex Networks and Overfitting

In the previous chapters, you have learned how to build and train complex networks. ...