Computational Learning Theory

What is computational learning theory?

Computational learning theory (CoLT) is a field of AI research studying the design of machine learning algorithms to determine what sorts of problems are learnable. The ultimate goals are to understand the theoretical underpinnings of deep learning programs, what makes them work or not while improving accuracy and efficiency.

Why use computational learning theory?

Computational learning theory provides a formal framework in which it is possible to precisely formulate and address questions regarding the performance of different learning algorithms. Therefore, it is possible to carefully compare the predictive power and the computational efficiency of competing learning algorithms.