CS3600 Summer 2018

Overview

You are on the page for information specific to the Summer 2018 session of this course. Go here Undergrad_Intro_AI_Course for overall course policies and information.

Office Hours

Dave: TTH 4:25-5:30, Klaus 2443. There is no class after us in our classroom, so I will simply stay there for up to an hour after every class, for as long as someone wants to talk to me! (If there does end up being a class after us, we will find another location.)

TA office hours: TBA.

Assignments and Grading

Projects (50%)

There will be four equally-weighted projects in the class, covering search algorithms, Markov decision processes, bayesian networks, and machine learning algorithms (decision trees and/or neural networks).

Exams (50%)

There is a midterm exam (20%) and a final exam (30%).

Extra Credit

The projects have significant extra credit built in. If you wish to maximize your grade, this is the place to do it. Requests for extra credit opportunities or free points at the end of the semester will be referred to this statement.

Thresholds

As mentioned on the main page, final course grades are not rounded up. While I understand the frustration of having your 89.9% become a B, you should understand that an 89.9% will typically place you in the bottom 30% of this class.

2018 Summer Schedule

This schedule is tentative and subject to change due to the compressed summer timeline. I am not certain exactly how quickly we will progress through the material.

The midterm will be given in week 6 or 7 depending on our progress. I will nail it down early in the class.

The final will be given according to the Registrar's schedule for final exams.

Week	Topic	Due
1	Intro to AI, Agents, Environments, Problem Solving, Search
2	Search, Informed Search	Intro Project (optional)
3	Informed Search, Probability	Search Project
4	Bayes Nets, Dynamic Bayes Nets
5	Particle Filtering, Intro Machine Learning	Bayes Net Project
6	Decision Trees, Midterm	Midterm
7	Decision Trees, Decision Making, Markov Decision Processes
8	Markov Decision Processes, Reinforcement Learning	Decision Trees Project
9	Local Search, Optimization
10	Neural Networks	MDP Project
11	Review for Final