### COMP9414/9814 Artificial Intelligence

## Review Questions on Machine Learning

This is a voluntary quiz to help you decide whether you have
understood some of the major concepts from this topic. It carries
no marks.

- What do dendrites, axon, and synapses, in a biological neuron, correspond
to in the artificial neuron model described in lectures?
- Why is a non-linearity used in the artificial neuron model described in
lectures? What are the important features of a suitable non-linearity?
- What is the weight change equation used by the error backpropagation
learning algorithm, and what do the symbols in this equation signify?
- What happens in the forward pass in error backpropagation learning?
What happens in the backward pass in error backpropagation learning?
- What does
*over-fitting* mean in the context of error backpropagation
learning?
- What is a decision tree?
- Give the formula for the
*entropy measure* used in lectures.
- Briefly, in words, describe how ID3 chooses the best attribute to split on.
- Give two reasons why there might be "noise" in training data.
- What is the formula for the Laplace error estimate?

Solutions: don't read until you've
tried the questions yourself!

Bill Wilson's contact info

© Bill Wilson, 2009

UNSW's CRICOS Provider No. is 00098G