Instances X: Possible days, each described by the attributes
Sky, AirTemp, Humidity, Wind, Water, Forecast
Target function c:
Hypotheses H: Conjunctions of literals. E.g.
Training examples D: Positive and negative examples of the target function
A hypothesis h in H such that h(x)=c(x) for all x in D.
- The inductive learning hypothesis: Any hypothesis found to approximate
the target function well over a sufficiently large set of training examples
will also approximate the target function well over other unobserved examples.