Logic of Machine Learning

I propose a new, logical, foundation for ML. ML is approached as a problem of maximizing consistency of a hypothesis in a context of a given training set. Nonjudgmental logic (NjL) with modalities ``It appears that'', ``Assume that'' is introduced to formalize and quantify the inconsistency. Many popular ML algorithms (from hierarchical clustering to k-NN and SVM) are shown to corroborate the conjecture. In addition, it is demonstrated that NjL allows to formalize and solve several general learning problems which are not considered as ML usually.