Pragmatic Theory of Machine Learning

C.S. Peirce understood pragmatism (pragmaticism) as a method of deriving new knowledge for practical use through explaining observations. But this is what machine learning (ML) is doing, essentially. A solution one infers in ML can be seen as the best explanation of the accumulated facts (the training set) intended for help in decision making. Peirce used the term \textbf{abduction} for this kind of inference. Here I formalize the concept of abduction for real valued hypotheses, and show that 14 of the most popular textbook ML learners (every learner I tested), covering classification, regression and clustering, implement this concept of abduction inference. The approach is proposed as an alternative to Statistical learning theory, which requires an impractical assumption of indefinitely increasing training set for its justification.