- To which of the two paradigms, learning with a teacher and
learning without a teacher, do the following algorithms belong?
Justify your answers.
- nearest neighbor rule
- k-nearest neighbor rule
- Hebbian learning
- error-correction learning

- Consider the difficulties that a learning machine faces in
assigning credit for the outcome (win, loss, or draw) of a game of
chess. Discuss the notations of temporal credit assignment and
structural credit assignment in the context of this game.
- A supervised learning task may be viewed as a reinforcement
learning task by using as the reinforcement signal some measure of the
closeness of the actual response of the system to the desired
response. Discuss this relationship between supervised learning and
reinforcement learning.
- Heteroassociative memory
, a matrix of size
, is a solution to the following group of equation systems:

where is the th input vector of size and is the corresponding desired output vector of size . The th equation of the th equation system can be written as follows:

where . Derive a gradient method which minimizes the following sum of squared errors:

How it is related to the LMS-algorithm (Widrow-Hoff rule)? - Show that
is a solution to the following group of
equation systems:

Vectors and are the th columns of matrixes and , respectively.

Jarkko Venna 2005-04-13