Regularization

Since deep neural networks are highly flexible models, overfitting is an issue that can often arise when training them. Therefore, one very important part of becoming a deep learning expert is knowing how to detect overfitting, and subsequently how to address the overfitting problem in your model. Overfitting in your models will be clear if your model performs excellently on the training data but performs poorly on new, unseen data.

For example, if you build a model to classify images of dogs and cats into their respective classes and your image classifier performs with high accuracy during the training process but does not perform well on new examples, then this is an indication that your model has overfitted the training data. Regularization techniques are an important group of methods specifically aimed at reducing overfitting in machine learning models.

Understanding regularization techniques thoroughly and being able to apply them to your deep neural networks...