Course Syllabus - Fall B 2019
Artificial Intelligence (CSE 571)
Course Description The field of Artificial Intelligence (AI) develops the principles and processes for designing autonomous agents. This course addresses the core concepts in designing autonomous agents that can reason, learn, and act to achieve user-given objectives and prepares students to address emerging technical and ethical challenges using a principled approach to the field. Main topics include principles and algorithms that empower modern applications and future technology development for self-driving vehicles, personal digital assistants, decision support systems, speech recognition and natural language processing, autonomous game playing agents and household robots.
Specific topics covered include:
● Neural Networks
● Classical Planning
● Modeling & Reasoning
● Reinforcement Learning
● Markov Decision Processes (MDPs)
● Partially Observable Markov Decision Processes (POMDPs)
● Bayesian Networks
● Sensors for Perception
● Perception based Recognition
● Real-world Applications
● Robotics
Learning Outcomes
Learners completing this course will be able to:
● Apply logical reasoning and programming to produce solutions for real-world problems.
● Use probabilistic inference to navigate uncertain information efficiently.
● Determine appropriate machine learning methods for a given scenario or dataset.
● Evaluate the challenges in perception systems for AI.
● Utilize sensors to execute perception tasks and their applications in intelligent systems.
● Apply algorithms to train an image classifier.
● Design an agent that can plan and act to achieve given objectives using noisy sensors and actuators.
Estimated Workload/ Time Commitment Per Week
Average of 15-20 hours per week
Required Prior Knowledge and Skills
● Proficient mathematical skills: Algebra, Linear Algebra, Probability and Statistics
● Experience using digital drawing tools (e.g. for constructing Parse Trees), Microsoft’s Office 365, installing software
● Strong Python and ROS skills
Technology Requirements
Hardware
● Personal computer with 8 GB RAM or higher
Software and Other
Reliable WiFi
Software and Other (programs, platforms, services, etc.)
● Matlab
● Ubuntu 16.04
● ROS Kinetic
● Turtlebot3 packages
● PyTorch ● GProlog 1.4.5
● Cygwin (Windows Users)
● Linux (Windows users may install virtual machines)
● Pip and Pgmpy
● Python 3.4 or higher
● Microsoft Office 365
Course Content
Instruction
Video Lectures and In-Video Questions Demonstration Videos Live Events (e.g. Live Sessions hosted by the faculty and Virtual Office Hours hosted by Teaching Assistants)
Assessments
In-Video Questions (ungraded, auto-feedback) Knowledge Check Questions (ungraded, auto-feedback) Assignments (graded, auto-graded and course team-graded) Individual Projects (graded, auto-graded) Practice Unit Quizzes (ungraded, auto-feedback) Unit Quizzes (graded, auto-graded) Practice Exams (ungraded, auto-feedback) Final Exam (graded, auto-graded, proctored)
Details of the main instructional and assessment elements this course:
Lecture videos: The concepts you need to know will be presented through a collection of video lectures. You may stream these videos for playback within the browser by clicking on their titles or download the videos. You may also download the slides that are used in the videos. The lecture slides, where available, are provided with the video.
In-Video Questions and Knowledge Checks: Designed to support your learning, in-video questions and knowledge checks are short ungraded quizzes to test your knowledge of the concepts presented in the lecture videos. You may take your time, review your notes, and learn at your own pace because knowledge checks are untimed. You may retake these as often as you would like at any point in the course. You are encouraged to read the feedback, review your answer choices, and compare them to the correct answers. With the feedback as your guide, you may use these as opportunities to study for other assessments and tasks in the course.
Discussion Forums: Discussion forums are present each week in the course. Although the course team is engaged in these discussions, the forums are spaces to clarify, support, and enrich student-to-student communication and learning.
Practice Quizzes: To help you prepare for other assessments in the course, you will have practice quizzes prior to taking graded quizzes and the proctored final exam. You may engage with your peers in the discussion forums to address questions, share resources and strategies, and provide feedback to help one another learn. You are encouraged to submit questions in the discussion forum for the course team to address during live events.
Graded Quizzes: Timed graded quizzes are included at the end of each week to assess you on each week’s content. They typically include 10 multiple choice questions. You will have 30 minutes to complete each quiz. Once you open the quiz, your testing session begins and you must complete it in a single session. You will be allowed one (1) attempt to take and complete each quiz. There is a 15% grade penalty for each day late past the deadline.
Proctored Final Exam: You will have one (1) proctored exam, which is a cumulative final exam (covering content from Weeks 1, 2, 3, 4, 5, 6, and 7). You have 120 minutes to complete the exam. Once you open the exam, your testing session begins and you must complete it in a single session. You will be allowed one (1) attempt to take and complete the exam. Students are allowed a calculator and no more than 6 piece of hard copy, handwritten notes on standard A-4 paper. No late exams will be permitted.
ProctorU is an online proctoring service that allows students to take exams online while ensuring the integrity of the exam for the institution. Additional information and instructions are provided in the Welcome and Start Here section of the course. You must setup your proctoring 72 hours prior to taking your exams, so complete this early.
Assignments and Projects: This course includes two (2) individual assignments and four (4) projects. Both are provided to students in the first week of the course, so you can review what is expected and design your own learning schedules to complete these on time. At the beginning of specific weeks when they are due, they will be re-introduced and included on your weekly task list at the beginning of each week. Projects and assignments are due at the end of the second week, third week, fifth week, and seventh week of the course. A submission area is provided at the end of these weeks. There are specified late penalties per assignment and project. Please review these carefully:
● Week 2 Assignment: Derivation of Logic Proofs - 10% grade penalty for each day late.
● Week 3 Assignment: Inference in Bayesian Networks - 10% grade penalty for each day late.
● Week 3 Project: Bayesian Networks - 15% grade penalty for each day late.
● Week 5 Project: Neural Network for Collision Prediction - 15% grade penalty for each day late.
● Week 7 Project: Tools for Sequential Decision-Making33% grade penalty for each day late.
Course Grade Breakdown
|
Course Work |
Quantity |
Percentage of
Grade |
|
Individual,
Timed Unit Quizzes |
8 |
32% |
|
Individual
Assignments |
2 |
6% |
|
Individual
Projects |
3 |
32% |
|
Individual,
Timed, Proctored Final Exam |
1 |
30% |
Grade Scale
|
A+ |
97% - 100% |
|
A |
90% - 96% |
|
B+ |
87% - 89% |
|
B |
80% - 86% |
|
C+ |
77% - 79% |
|
C |
70% - 76% |
|
D |
60% - 69% |
|
E |
<60% |
|
Week/Module |
Begin Date |
End Date |
|
Week 1:
Introduction to Artificial Intelligence |
10/16 |
10/20 |
|
Week 2:
Modeling |
10/21 |
10/27 |
|
Week 3:
Reasoning |
10/28 |
11/3 |
|
Week 4:
Machine Learning Part 1 |
11/4 |
11/10 |
|
Week 5:
Machine Learning Part 2 |
11/11 |
11/17 |
|
Week 6:
Perception |
11/18 |
11/24 |
|
Week 7:
Sequential Decision-Making |
11/25 |
12/1 |
|
Final Exam |
11/29 |
12/2 |
|
Week 8:
Course Wrap-Up |
12/2 |
12/6 |
*Grades are due December 9th, 2019 (Please see the ASU Academic Calendar for additional information.)
Dr. Yezhou Yang
Yezhou Yang, Ph.D. is an Assistant Professor at the School of Computing, Informatics, and Decision Systems Engineering (CIDSE), Arizona State University (ASU), directing the Active Perception Group (APG). He received his M.S. and Ph.D. degrees in Computer Science from the University of Maryland at College Park in 2013 and 2015 respectively. Prior to that, he obtained a B.Eng. degree in Computer Science and Engineering from Zhejiang University,
China. His primary research focus is in Computer Vision and Robot Vision, especially exploring visual primitives in interpreting peoples’ actions and the scene’s geometry from visual input, grounding them by natural language as well as high-level reasoning over the primitives for intelligent systems. His research mainly focuses on solutions to visual learning, which significantly reduces the time to program intelligent agents. He is a recipient of Qualcomm Innovation Fellowship 2011, Verisk AI faculty award, and the NSF CAREER award in 2018.
Dr. Siddharth Srivastava
Siddharth Srivastava, Ph.D. is an Assistant Professor of Computer Science in the School of Computing, Informatics, and Decision Systems Engineering (CIDSE) at Arizona State University (ASU). Prof. Srivastava was a Staff Scientist at the United Technologies Research Center in Berkeley. Prior to that, he was a postdoctoral researcher in the RUGS group at the University of California Berkeley. He received his Ph.D. in Computer Science from the University of Massachusetts Amherst. His research interests include robotics and AI, with a focus on reasoning, planning, and acting under uncertainty. His work on integrated task and motion planning for household robotics has received coverage from international news media. His dissertation work received a “Best Paper” award at the International Conference on Automated Planning and Scheduling (ICAPS) and an Outstanding Dissertation award from the Department of Computer Science at UMass Amherst.
Dr. Yu “Tony” Zhang
Yu (“Tony”) Zhang, Ph.D. is an Assistant Professor at Arizona State University (ASU), where he directs the Cooperative Robotic Systems (CRS) laboratory. He graduated with a Ph.D. degree in Computer Science from the University of Tennessee, Knoxville in 2012. His research interests include the intersection of artificial intelligence (AI) and robotics. The focuses are innovating and applying AI and machine learning methods to human-robot teaming, multi-agent systems, distributed robotic systems, and more generally, human-in-the-loop AI systems. His research has been funded by federal governments and agencies, such as the National Science Foundation (NSF), National Aeronautics and Space Foundation (NASA) and Air Force of Scientific Research(AFOSR). Zhang has been highlighted with “Best Paper” Awards in premier robotics conferences. He is also a member/senior member of the program committees of major AI and robotics conferences, such as AAAI, IJCAI, IROS, and ICRA.
