MACHINE LEARNING

Hypothesis Space

•         One way to think about a supervised learning machine is as a device that explores a “hypothesis space”.

–        Each setting of the parameters in the machine is a different hypothesis about the function that maps input vectors to output vectors.

–        If the data is noise-free, each training example rules out a region of hypothesis space.

–        If the data is noisy, each training example scales the posterior probability of each point in the hypothesis space in proportion to how likely the training example is given that hypothesis.