Note: The syllabus is subject to change.

Course Description

This course will introduce the basic ideas and techniques underlying the design of intelligent agents to enable them to act and "think" like humans. The topics covered include problem-solving via search, game playing, logical and probabilistic reasoning, machine learning (decision trees, linear models, neural networks, and reinforcement learning). A key aspect of this course is the presence of several hands-on projects that will help to concertize the fundamental methods studied.
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.

The course will have a hybrid structure: Synchronous online and residential. What does this mean? Lectures will be broadcast during class time. You can either attend the class physically or virtually (see below for tools and restrictions). All materials will be made available for later consultation.

Online Tools, Restrictions, and Classroom Behavior

Attendance

To comply with the health safety University policy and enforce social distancing, students will be allowed to participate in-class only every other lecture. A list and seat assignment will be released prior to the start of the first class.
Regardless of your in-class participation turn, you are encouraged to follow the classes online.

Restrictions

• Wear a mask: This is mandatory. No student, TA, or faculty, will be allowed, at any time, to remove her/his mask.
• Respect social distancing rules: You will need to be at least 6ft apart from other individuals. This rule must be enforced during class and while transiting in the classroom (e.g., to join/leave the class).
• Bring your own laptop or smartphone and headphones. We will alternate lecture content with class activities ran asynchronously with other students attending online.
• No eating/drinking: This is a strict rule.

Online Tools

We will use different systems to enhance the class experience, and to best respond to the issues rose by the current pandemic.

• Zoom: All lectures will be accessible, synchronously, via a zoom link provided in the blackboard course page.
• Discord: Group activities performed during class, FAQ, and homework/project discussions will take place on the class Discord channel.
• Gradscope: Homework, Projects, and Exam will be submitted and graded using the Gradscope course page.
• Blackboard: It contains the recorded video lectures associated with each class.

Prereq

• CIS 375 and CIS 321 and (CIS 351 or CSE 382)
• Knowledge of Python. This will be critical to complete the projects. Students may not have strong experience with the language, but we do expect you to learn the basics very rapidly. Project 0 is designed to teach you the basics of Python.
  If you want to follow some extra good tutorial, try the ACM Python Tutorial

If you are unsure about any of these, please speak to the instructor.

Communication

There will be several routes of communication for this course:

• Discord Channel The main mode of electronic communication between students instructors and TAs, as well as amongst students, is through Discord. It is intended for general questions about the course, clarifications about assignments, student questions to each other, discussions about the material, and so on. We strongly encourage students to participate in discussions, ask, and answer questions.
• Email: If you need to contact the course staff privately, you should email cis467fall20@gmail.com. Emails sent to the instructor's or TAs' email addresses may not receive an answer.

Textbook and Online Material

• Course textbook: Artificial Intelligence, A Modern Approach (3rd edition) by Russell and Norvig and published by Prentice Hall (ISBN: 0136042597).
• Online Material: Dive into Deep Learning by Aston Zhang, Zachary C. Lipton, Mu Li, and Alexander J. Smola
• AIMACODE Python

Assignments

This class includes 11 homework, several quizzes, 4 programming projects, 2 mini-exams, and 1 final exam. Homework, quizzes, and exams are handled electronically on the gradscope course page

Late Policy

• Homework cannot be turned in late, you have to use your homework drops.
• Projects lose 20% of their total point value per day turned in late.

Collaboration

• Homework are to be submitted individually, but may be discussed in groups. If discussed in a group, acknowledge your collaborators.
• Project 0 is to be completed individually.
• Projects 1 through 4 can be completed alone or in teams of two. If done in a team of two, the person who submits needs to tag the other team member on Gradescope.

Homework Drop Policy

You will be allowed to drop your 3 lowest homework. These may be distributed throughout the semester. When calculating final grades, this will happen automatically, we’ll just use your highest scoring submissions.
Note that this policy is also meant to deal with cases like internet issues while submitting, forgetting about the deadline, emergency situations (including medical).

Exams

There will be 2 mini-exams and 1 final exam. Both mini-exams and the final exam are open-book and open-notes.
They will all be performed online (on gradscope). From the moment the exam is released you will have 24 hours to start it. Once you start your exam, you will have a designed amount of time to turn it in. There will be no make-up exams unless there is a medical document that justifies the absence.

Grading

• Homework Assignments: 25%
• Programming Assignments: 25%
• Class Activities (Quizzes and group assignments): 5%
• Mini-exam 1: 10%
• Mini-exam 2: 10%
• Final Exam: 25%
• Bonus (contests): up to 8%

Grading Scale

The grading scale is fixed and as follows.

Grade	Overall Percentage	Grade	Overall Percentage
A	[85, 100]	C	[55, 60)
A-	[80, 85)	C-	[50, 55)
B+	[75, 80)	D+	[45, 50)
B	[70, 75)	D	[40, 45)
B-	[65, 70)	D-	[35, 40)
C+	[60, 65)	F	[0, 35)

For more information about letter grades, including in the event of withdrawal, drop, or incomplete, see Grades and Grading Symbols in Academic Rules (Academic Catalog, Academic Rules Section 8.4.1).
For academic support services such as tutoring, see the Center for Learning and Student Success.

Regrade Policy

If you believe an error has been made in the grading of one of your exams or assignments, you may resubmit it for a regrade. Regrades for cases where we misapplied a rubric in an individual case is much more likely to be successful than regrades that argue about relative point values within the rubric, as the rubric is applied to the entire class.
Because we will examine your entire submission in detail, your grade can go up or down as a result of a regrade request.

SU Stay Safe Pledge

Syracuse University’s Stay Safe Pledge reflects the high value that we, as a university community, place on the well-being of our community members. This pledge defines norms for behavior that will promote community health and wellbeing. Classroom expectations include the following: wearing a mask that covers the nose and mouth at all times, maintaining a distance of six feet from others, and staying away from class if you feel unwell. Students who do not follow these norms will not be allowed to continue in face-to-face classes; repeated violations will be treated as violations of the Code of Student Conduct and may result in disciplinary action.


University-wide Policies

Students should review the University’s policies regarding:
• Diversity and Disability
• Religious Observances Notification and Policy
• Orange SUccess
• Non-discrimination and STOP Bias
• All Other Academic Rules

Disability-Related Accommodations

If you believe that you need academic adjustments (accommodations) for a disability, please contact the Office of Disability Services (ODS), visit the ODS website, located in Room 309 of 804 University Avenue, or call (315) 443-4498 or TDD: (315) 443-1371 for an appointment to discuss your needs and the process for requesting academic adjustments. ODS is responsible for coordinating disability-related academic adjustments and will issue students with documented Disabilities Accommodation Authorization Letters, as appropriate. Since academic adjustments may require early planning and generally are not provided retroactively, please contact ODS as soon as possible.

Diversity and Disability

Syracuse University values diversity and inclusion; we are committed to a climate of mutual respect and full participation. My goal is to create learning environments that are useable, equitable, inclusive, and welcoming. If there are aspects of the instruction or design of this course that result in barriers to your inclusion or accurate assessment or achievement, I invite you to meet with me to discuss additional strategies beyond academic adjustments that may be helpful to your success.

Academic Integrity

Any instance of sharing or plagiarism, copying, cheating, or other disallowed behavior will constitute a breach of ethics. Students are responsible for reporting any violation of these rules by other students, and failure to constitutes an ethical violation that carries with it similar penalties. SU students are required to read an online summary of the University’s academic integrity expectations and provide an electronic signature agreeing to abide by them twice a year during pre-term check-in on MySlice. For more information about the policy, see the policy website.