Weighing Hypotheses: Incremental Learning from Noisy Data

Incremental learning from noisy data presents dual challenges: that of evaluating multiple hy-potheses incrementally and that of distinguishing errors due to noise from errors due to faulty hy-potheses. This problem is critical in such areas of machine learning as concept learning, inductive programming, and sequence prediction. I develop a general, quantitative method for weighing the merits of different hypotheses in light of their per-formance on possibly noisy data. The method is incremental, independent of the hypothesis space, and grounded in Bayesian probability