2. A very good repository of data that has been used to test the performance of neural network and other machinelearning algorithms can be accessed at ics.uci.edu/

~mlearn/MLRepository.html. Some of the datasets are really meant to test the limits of current machine-learning algorithms and compare their performance against new approaches to learning. However, some of the smaller datasets can be useful for exploring the functionality of the software you might download in Internet Exercise 1 or the software that is available at StatSoft.com (i.e., Statistica Data Miner with extensive neural network capabilities).

Download at least one dataset from the UCI repository

(e.g., Credit Screening Databases, Housing Database).

Then apply neural networks as well as decision tree methods, as appropriate. Prepare a report on your results.

(Some of these exercises could also be completed in a group or may even be proposed as semester-long projects for term papers and so on.)