next up previous
Next: Store v Compute Up: Learning I Previous: How can we learn?

Rote Learning

Rote Learning is basically memorisation.

A simple example of rote learning is caching

Memorisation is a key necessity for learning:

Samuel's Checkers program employed rote learning (it also used parameter adjustment which will be discussed shortly).

Rote learning is basically a simple process. However it does illustrate some issues that are relevant to more complex learning issues.

Organisation
-- access of the stored value must be faster than it would be to recompute it. Methods such as hashing, indexing and sorting can be employed to enable this.

E.g Samuel's program indexed board positions by noting the number of pieces.

Generalisation
-- The number of potentially stored objects can be very large. We may need to generalise some information to make the problem manageable.

E.g Samuel's program stored game positions only for white to move. Also rotations along diagonals are combined.

Stability of the Environment
-- Rote learning is not very effective in a rapidly changing environment. If the environment does change then we must detect and record exactly what has changed -- the frame problem.




next up previous
Next: Store v Compute Up: Learning I Previous: How can we learn?

dave@cs.cf.ac.uk