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).
| eigenvector | linear associator | autoassociator | synaptic modification |
| Hebbian | heteroassociation | coarse coding | spontaneous activity |
| leaky integrator | perceptron | projective field | BSB |
| dendrite | classical conditioning | receptive field | lateral inhibition |
| spike | linear independence | grandmother cell | XOR |
| McCulloch-Pitts | distinctive features | cross-correlation | supervised learning |
| recurrent inhibition | pseudoinverse | gradient descent | symmetric matrix |
| WTA | least-squares | linear system | orthogonality |
| outer product learning | Widrow-Hoff error correction | topographic representation | generic neural network neuron |
Sample essay questions
(choice of 2 essays drawn from a subset of about 6 of those listed below;
12 points each).
Describe the anatomy of the generic neuron, and the mechanisms involved
in the generation of an action potential .
Discuss Anderson's model of either auto- or hetero-associative learning. Give one example of its application..
What is the Perceptron model? Discuss both its successes, failures and impact on the field of neural network research.
Describe a neural network model for the lateral eye of the limulus. Relate a dynamical model to possible retrieval mechanisms for autoassociation.
Discuss the pros and cons of distributed vs. localized representations with examples from theoretical considerations and neurophysiology.
Contrast "connectionist" computational schemes with traditional serial computing.
Problem
(One problem, 3 to 6 points)
You should be able to compute inner and outer products, multiply matrices
and vectors, calculate the transpose, know how to find eigenvectors and
eigenvalues, measure the "similarity" between vectors, and find
the inverse of small (e.g. 2x2) matrices.