Introduction to Neural Networks
U. of Minnesota, Final Study Guide
Psy 5038

Spring, 1998


The final will cover material in the Anderson book, chapters 9, 10, 12, 13 (very little), 14, 15.
There may be some material from the first half of the quarter, but the final exam
will be heavily weighted towards the second half of the quarter.

Sample short answer questions
Define and describe the relation of the following key words or phrases to neural networks.
(8 items drawn from set below; 3 points each).

"Energy"	attractor	pseudoinverse	BSB
autoassociator	topographic representation	grandmother cell	asynchronous update
Content addressable memory	Oja's rule	principal components analysis	sparse distributed representation
constraint satisfaction	nearest-neighbor classifier	diameter-limited	correspondence problem
gradient descent	Lyapanov function	encoder network	topology-preserving map (Kohonen)
simulated annealing	cortical maps	generalized delta rule	Widrow-Hoff error correction
XOR	Hopfield's continuous response model	Gibbs G measure	anti-Hebbian
perceptron learning rule	random dot stereogram	prototype/exemplar	local minimum

Sample essay questions
(choice of 2 essays drawn from a subset of those listed below; 12 points each).

Give an account of Hopfield's 1984 graded response neural network model. How does it relate to the discrete stochastic model of 1982?

Describe Marr and Poggio's 1976 stereo algorithm, and compare it to Hopfield's 1982 neural network.

How does the error back-propagation model work (you don't need to derive the learning rule)? What are the pros and cons of this learning algorithm?

Describe the Boltzmann machine learning algorithm (you need not derive the learning rule). What are the pros and cons of this learning algorithm?

Give an account of just one of the following approaches to self-organization: Kohonen, 1982 (Chapter 14); or principal components sub-spaces.

Describe Anderson's Brain-state-in-a-box model using one application.