Introduction to AI

It is difficult to think of a major industry that AI will not transform. This includes healthcare, education, transportation, retail, communications, and agriculture. There are surprisingly clear paths for AI to make a big difference in all of these industries.

Andrew Ng
Russell, S. J., & Norvig, P. (2022). Artificial intelligence: a modern approach. Malaysia; Pearson Education Limited.

Welcome to the world of Artificial Intelligence (AI). In this course, we will learn to develop techniques that would provide software and hardware systems the opportunity to ‘think‘ by themselves.

Primarily, three pillars of AI will be covered in this course:

  • Searching: how to search for a solution in a large solution space, e.g., search for a path from location A to B.
  • Planning: how to plan your actions according to the different states of the environment, e.g., plan to clean a room using a Roomba vacuum cleaner.
  • Learning: how to learn from your collected data and/or your past actions, e.g., how a robotic arm can learn to manipulate an object.

The students will complete assignments and project(s) in order to pass the course. Topics that will be covered in this course are listed below:

  1. Chapters 1 and 2: Introduction.
  2. Chapter 3. Classical searching.
  3. Chapter 4. Advanced search.
  4. Chapter 5. Game Theory.
  5. Chapter 6: CSP.
  6. Chapter 13: Uncertainty.
  7. Chapter 14: Probabilistic Reasoning.
  8. Chapter 16: MDP.
  9. Chapter 18: Supervised learning.
  10. Chapter 21: Reinforcement Learning.

Instructor Information

Professor: Dr. Ayan Dutta

Please allow 24-48 hours to receive a response to your email if it is related to current lecture material or assignments.  Allow slightly longer otherwise.

Performance Evaluation Scale

Letter Grade  Final Score Range 
A≥ 93.00%
A-90.00 – 92.99%
B+87.00 – 89.99%
B83.00 –  86.99%
B-80.00 – 82.99%
C+75.00 – 79.99%
C70.00 – 74.99%
D60.00 – 69.99%
F< 60.00%

Student Responsibilities

  • Class attendance is essential. 
  • To avoid disruptions, please turn off or silence all cell phones, pagers, and similar electronic devices during classes and exams.
  • Any electronic devices, such as a laptop, lab computer, and other electronic device utilization, in class, are only allowed if used for the AI class-related purposes. The connection of electronic devices to the network for surfing the Internet, personal use, and any other non-related course usage is inappropriate and is prohibited during the class.
  • Personal lecture notes should be used for class and not posted for any group other than class members.
  • Video, audio, or pictures should not be taken during the class unless there is prior permission.
  • Plagiarism will not be tolerated and will result in grade F for the course.
  • To get the most out of this class:
    1. Attend all of the lectures.
    2. Read the chapters from the textbook.
    3. Start early on your assignments/projects.
N.B. All the SoC and UNF policies will be enforced.

Examples of student work (Spring 2023)

A paper titled “Kepler Light Curve Classification Using Deep Learning and Markov Transition Field (Student Abstract)” has been accepted for publication at the 38th AAAI conference.

The lead author of this paper is Mr. Shane Donnelly who is an undergraduate computing student at UNF. The work presented in this paper is an extension of his class project in the Intro to AI course (spring 2023).

Examples of student work (Fall 2020)

Visualization of “Burgard, W., Moors, M., Stachniss, C., & Schneider, F. E. (2005). Coordinated multi-robot explorationIEEE Transactions on Robotics21(3), 376-386.” by Brian Sotolongo.

by Mr. Brian Sotolongo (Fall 2020).

Examples of student work (Fall 2019)

Visualization of “Potential-based bounded-cost search“[Stern 2014] implementation on custom environments.

[Benjamin Samples; the top environment is from the AI book, Fig. 3.31]

Path planning GIF[Joshua Nelson: path planning GIF]

Coverage with 3 (above) and 5 (below) robots with continuous connectivity [Justin Reynoso]
Reference: Rooker, M. N., & Birk, A. (2007). Multi-robot exploration under the constraints of wireless networking. Control Engineering Practice15(4), 435-445.
ARA* [Benjamin Samples]