Summary
In this chapter, you learned about two very important groups of techniques for improving the accuracy of your deep learning models: regularization and hyperparameter tuning. You learned how regularization helps address the overfitting problem by means of several different methods, including L1 and L2 norm regularization and dropout regularization—the more commonly used regularization techniques. You discovered the importance of hyperparameter tuning for machine learning models and the challenge of hyperparameter tuning for deep learning models in particular. You even practiced using scikit-learn optimizers to perform hyperparameter tuning on Keras models.
In the next chapter, you will explore the limitations of accuracy metrics when evaluating model performance, as well as other metrics (such as precision, sensitivity, specificity, and AUC-ROC score), including how to use them in order to gauge the quality of your model's performance better.
