This semester’s AI course will focus on the sub field of machine learning with some work in the analysis of big data. We will look at classic unsupervised and supervised learning methods, used in the field to classify data, cluster it and find optimizations. This will include looking at k-means and hierarchical clustering, self-organizing maps, linear regression, decision trees, optimization techniques such as genetic algorithms, etc. We will cover ways of getting hold of interesting datasets, ideas on how to collect data from users, and many different ways to analyze and understand the data once you’ve found it.
- Explore downloading and mining real web data sets.
- Learn about unsupervised methods for grouping and visualization.
- Program optimization algorithms to search for optimal solutions using hill climbing, GA’s, etc.
Become familiar with some advanced classification techniques of the kernel methods family of algorithms.