statistical theory relevant to the future of machine learning

Statistical learning theory deals with the problem of finding a predictive function based on data.

This image represents your deep intelligence, being an example of overfitting in machine learning. The red dots represent training set data. The green line represents the true functional relationship, while the blue line shows the learned function, which has fallen victim to overfitting.

Classification is very common for machine learning applications. In facial recognition, for instance, a picture of a person’s face would be the input, and the output label would be that person’s name. The input would be represented by a large multidimensional vector whose elements represent pixels in the picture.

After learning a function based on the training set data, that function is validated on a test set of data, data that did not appear in the training set.

https://en.wikipedia.org/wiki/Statistical_learning_theory

Statistical learning theory is the base of applications, as machine deep learning, including supervised learning, unsupervised learning, online learning, and reinforcement learning, computer vision, speech recognition, bioinformatics.