Consistency of Learning Processes
The goal of this part of the theory is to describe the conceptual model for learning processes that are based on the Empirical Risk Minimization inductive principle. This part of the theory has to explain when a learning machine that minimizes empirical risk can achieve a small value of actual risk (can generalize) and when it can not. In other words, the goal of this part is to describe the necessary and sufficient conditions for the consistency of learning processes that minimizes the empirical risk.
KeywordsProbability Measure Indicator Function Uniform Convergence Elementary Event Inductive Inference
Unable to display preview. Download preview PDF.