Artificial Intelligence – S’21

This syllabus is informational in nature and is not an express or implied contract. It is subject to change due to unforeseen circumstances, as a result of any circumstance outside the University’s control, or as other needs arise. If, in the University’s sole discretion, public health conditions or any other matter affecting the health, safety, upkeep or wellbeing of our campus community or operations requires the University to make any syllabus or course changes or move to remote teaching, alternative assignments may be provided so that the learning objectives for the course, as determined by the University, can still be met. The University does not guarantee that this syllabus will not change, nor does it guarantee specific in-person, on-campus classes, activities, opportunities, or services or any other particular format, timing, or location of education, classes, activities, or services.

Modality:

This class is FLEX. This means that approximately half the class will be in person and the other half online via Zoom one day and then flip the halves the other day of the week.

Based on the letter of their last name, commuters have been told what day they are meeting in person and what day online. Residential students will be distributed over the two days to “even out” the in class numbers. There may be a third category of student that is online only, but this must be discussed and agreed to with the student’s advisor, the instructor, and the Covid Task Force.

Students cannot switch in person days.

Course Description:

Prerequisite: CSCI 6602 or equivalent course in Python.

An introduction to the fundamental methods of artificial intelligence (AI) used in problem solving. Techniques include heuristic search, optimization, genetic algorithms, game playing, expert systems, probabilistic reasoning, learning strategies, neural networks, natural language understanding, image understanding. 3 credits.

This course will introduce the basic ideas and techniques underlying the design of intelligent computer systems. A specific emphasis will be on the statistical and decision theoretic modeling paradigm.

Required Text(s):

Russell & Norvig, AI: A Modern Approach, 3rd edition. Note that the slides and other course material do not necessarily follow the presentation in this book.

Course Structure/Course Format/Course Objectives:

This class is offered as a hybrid course: will combine online asynchronous (i.e., pre-recorded) lectures, in-person and online tutorial/discussion sessions, written and online assignments, and programming projects. Active learning will constitute as much as 50% of the class. Participation will be recorded based on engagement in discussions (online/in-person), as well as submitted assignments.

Course Objectives:

By the end of this course, you will have built autonomous agents that efficiently make decisions in fully informed, partially observable and adversarial settings. Your agents will draw inferences in uncertain environments and optimize actions for arbitrary reward structures. Your machine learning algorithms will classify handwritten digits and photographs. The techniques you learn in this course apply to a wide variety of artificial intelligence problems and will serve as the foundation for further study in any application area you choose to pursue.

Student Learning Outcomes:

By the end of this course, students will be able to:

1. Build autonomous agents that efficiently make decisions in fully informed, partially observable and adversarial settings.
2. Create an agent that will draw inferences in uncertain environments and optimize actions for arbitrary reward structures.
3. Create a machine learning algorithm that will classify handwritten digits and photographs.

Course Requirements & Assessment:

Please see official University of New Haven Academic Policies located in the links below:

• Undergraduate Grading System
• Graduate Grading System

Assignments/Projects:

• All submissions are online, either via Canvas or Gradescope (as instructed in the assignment details). Please turn in whatever you have for participation credit, event if incomplete.
• Homework assignments can be completed via pen and paper, but the final submission must be scanned/photographed copies of the work. If handwriting is deemed illegible there may be a penalty, or the attempt may be completely reject.

Examinations:

• This course will have two exams: midterm and final. Both exams are take-home and open-book, but must be completed individually. The exams will include questions taken directly from the class discussions and exercises. Exams may also require handwritten code. Everything you are told or shown in class is fair game, not just the content of slides.

Participation:

Active learning will constitute as much as 50% of the class. Participation will be recorded based on engagement in discussions (online/in-person), as well as submitted assignments.

Grading:

Grades earned are based on your performance on homework, projects, the midterm and the final exam. The weight of each component is outlined below:

Programming Assignments	25%
Electronic Homework Assignments	15%
Written Assignments	15%
Final Project	10%
Midterm Exam	10%
Final Exam	15%
Total**	100%

Typical Undergraduate Scale	Typical Graduate Scale
Grades Scored Between & it’s Letter Equivalent	Grades Scored Between & it’s Letter Equivalent
97 to 100 — A+	97 to 100 — A+
94 to Less than 97 — A	94 to Less than 97 — A
90 to Less than 94 — A-	90 to Less than 94 — A-
87 to Less than 90 — B+	87 to Less than 90 — B+
84 to Less than 87 — B	84 to Less than 87 — B
80 to Less than 84 — B-	80 to Less than 84 — B-
77 to Less than 80 — C+	77 to Less than 80 — C+
74 to Less than 77 — C	74 to Less than 77 — C
70 to Less than 74 — C-	70 to Less than 74 — C-
67 to Less than 70 — D+	Less than 70 — F
63 to Less than 67 — D
60 to Less than 63 — D-
Less than 60 — F

Expectations:

Students should expect to spend at least 3 hours on academic studies outside, and in addition to, each hour of class time. There will be readings, homework questions/problems, and programming projects.

Late Work:

Assignments turned in late may be accepted with a grade penalty, if the solutions are not distributed yet. This is completely at the discretion of the instructor, as the goal is to balance learning and fairness.

Missed Work:

Exams may be made up in only the most unavoidable situations (at the discretion of the instructor). A formal excused absence (such as a note from Health Services or a healthcare provider) will be required before you can make up a missed exam.

Individual Work:

Students must work individually on assignments and projects unless specifically allowed to work in groups by the instructor. Any work taken from the internet must be cited properly (acceptance of code taken from elsewhere is at the discretion of the instructor) or will be considered plagiarism. Failure to adhere to this policy will result in penalties ranging from a zero on the assignment to a zero in the final grade. Students may also be subject to disciplinary action by the University of New Haven (see University Policies).

Course Outline/Schedule:

Day/Date	Topic/Note	Day/Date	Topic/Note
1/21	Intro to AI	3/23	BNs: Inference
1/26	Uninformed Search	3/25	BNs: Sampling
1/28	A* Search and Heuristics	3/30	Decision Networks / VPI
2/2	CSPs I	4/1	Particle Filtering and Apps of HMMs
2/4	CSPs II	4/6	ML: Naïve Bayes
2/9	Game Trees: Minimax	4/8	ML: Perceptrons and Logistic Regression
2/11	Game Trees: Expectimax, Utilities	4/13	ML: Optimization and Neural Networks
2/16	MDPs I	4/15	ML: Neural Networks II and Decision Trees
2/23	MDPs II	4/20	Robotics / Language / Vision
2/25	RL I	4/22	AI Safety, Security, and Ethics
3/2	RL II	4/27	Project Presentations
3/4	Probability	4/29	Project Presentations
3/11	Midterm Exam	5/4	Final Review
3/16	BNs: Representation	5/10	Final Exam
3/18	BNs: Independence

Reporting Bias Incidents:

At the University of New Haven, there is an expectation that all community members are committed to creating and supporting a climate which promotes civility, mutual respect, and open-mindedness. There also exists an understanding that with the freedom of expression comes the responsibility to support community members’ right to live and work in an environment free from harassment and fear. It is expected that all members of the University community will engage in anti-bias behavior and refrain from actions that intimidate, humiliate, or demean persons or groups or that undermine their security or self-esteem. (Reporting Options).

University-wide Academic Policies:

A continually-updated list of University-wide academic policies and descriptions of key university student resources, can be found on Canvas.  You can access them by simply clicking on the (?) help button.

The University-wide academic policies include (but are not limited to) the University’s attendance policy, procedures for both adding / dropping a course and course withdrawals, an explanation for the sorts of circumstances where incomplete (INC) grades could be considered by the faculty, and the academic integrity policy (among others).  Also in this location you will find information regarding the process for reporting bias and topics related to our maintaining a positive learning environment (including, but not limited to, discrimination and sexual misconduct). 

The list of key university student resources to enable learning include (but are not limited to) the University’s Center for Student Success, Writing Center, Center for Learning Resources, and the Accessibility Resource Center.