Next: Inductive Biases of Algorithms
Up: Concept Learning
Previous: Futility of Bias-Free Learning
- Consider a concept learning algorithm
for the set of
instances 
. Let 
be an arbitrary concept defined over
, and let 
be an arbitrary set of
training examples of . Let 
denote the
classification assigned to the instance 
by after
training on the data 
. The inductive bias of is
any minimal set of assertions 
such that for any target concept
and corresponding training examples 
- Inductive bias of the Candidate-Elimination algorithm. The
target concept is contained in the given hypothesis space
.
Patricia Riddle
Fri May 15 13:00:36 NZST 1998