|Instructor Info:||Jaime Davila|
Office Extension x5687
This course will expose students to several mayor artificial intelligence (AI) techniques. For each of these techniques we will start by looking at basic definitions and theoretical considerations, followed by looking at open source software packages that implement the AI approach, and then how to use these software packages for decision-making step within larger applications. Techniques we will look at include: searching, decision trees, Bayesian networks, artificial neural networks, evolutionary computation, and programmable logic. By the end of the semester successful student will understand the theoretical foundations of each approach, and will be equipped to correctly choose which approach to use for different needs. Prerequisite: a semester of college level programming
By the end of the course successful students will know the theory on several of the most important artificial intelligence techniques. They will also know how to locate, install, and use software that implement these techniques, and will have used them in appropriately to solve problems of their own choosing.
Students will be evaluated based on the appropriate implementation of several projects, each of them using one of the main sections of the course (searching, induction of decision trees, artificial neural neural networks, bayesian networks, evolutionary computation, and programmable logic). For each of these topics, students will both hand in code and give in-class oral presentations.
Textbook (optional but very much recommended): Artificial Intelligence: A New Synthesis, by Nils J. Nilsson.
Skip Course Information