Mastering Machine Learning Algorithms

Training and validation sets

In real problems, the number of samples is limited, and it's usually necessary to split the initial set X (together with Y) into two subsets as follows:

• Training set used to train the model
• Validation set used to assess the score of the model without any bias, with samples never seen before

According to the nature of the problem, it's possible to choose a split percentage ratio of 70% – 30% (a good practice in machine learning, where the datasets are relatively small), or a higher training percentage (80%, 90%, up to 99%) for deep learning tasks where the number of samples is very high. In both cases, we are assuming that the training set contains all the information required for a consistent generalization. ...