nFind best function that models given data.
n
nHow to define the best function?
¡Fidelity to the data – error on existing data:
E(h,D)
¡Simplicity – how complicated is the solution: C(h)
nOne measure: how many possible hypotheses for the
class?
n
nInevitable tradeoff between complexity of hypothesis and degree of fit to the data
n
nMinimize α E(h,D) + (1-α) C(h)
¡Where
α
is a tuning parameter