CPSC 383: Explorations in Artificial Intelligence and Machine Learning (Winter 2026)


A survey of artificial intelligence and machine learning tools to cultivate an understanding of their capability, utility, and societal/ethical/legal considerations. Popular APIs will be used to develop simple applied examples.

Announcements

  • Website under construction.

Lectures

  • Lectures begin on Monday, January 12th, 2026
  • Last day to drop is Thursday, January 22nd, 2026
  • Last day to add is Friday, January 23rd, 2026
  • Lectures end and last day to withdraw is Tuesday, April 14th, 2026
  • CPSC 383 L01 MonWedFri 12:00-12:50 TI 160

Tutorials

  • Tutorials will begin on Monday/Tuesday, January 19th/20th, 2026
  • The main goals of the tutorials will be to help you in more deeply understanding the concepts presented in the lectures through graded in-person worksheets and help for your assignments.
  • CPSC 383 T01 MonWed 13:00-13:50 MS 252 Parham MoonesiSohi parham.moonesisohi@ucalgary.ca
  • CPSC 383 T02 MonWed 14:00-14:50 MS 252 Mahdi FarrokhiMaleki mahdi.farrokhimaleki@ucalgary.ca
  • CPSC 383 T03 TueThu 08:00-08:50 MS 252 Amin Zeinali amin.zeinali@ucalgary.ca
  • CPSC 383 T04 TueThu 09:00-09:50 MS 252 Matthew McConnell matthew.mcconnell1@ucalgary.ca
  • CPSC 383 T05 TueThu 13:00-13:50 MS 176 Parham MoonesiSohi parham.moonesisohi@ucalgary.ca

Office Hours

  • MonWed 13:00-13:50 ICT 712 or setup via email (info in D2L Content)

Important Dates

  • Term Break: Sunday-Saturday, February 15-21st, 2026. (no lectures or tutorials)
  • University Closed for Alberta Family Day Monday, February 16th, 2026. (During term break, No office hours)
  • University Closed for Good Friday Friday, April 3rd, 2026. (No lecture/No tutorial/No office hours)
  • University Closed for Easter Monday Monday, April 6th, 2026. (No lecture/No tutorial/No office hours)

Textbook Resources (!!Extremely Optional!!)

  • Artificial Intelligence: A Modern Approach 4e (2021)
    • Author: Russell Norvig
    • ISBN: 9780134610993
    • Optional: For those who appreciate another resource. Taught material diverges from this source.
    • Version 3e likely just as good for your purposes.

The due dates for the assignments can be found in the Assignments sections of this page.

Support Materials

  • Course Information Sheet (Outline)
  • Organization pdf
  • Topics
    • Part 1: AI and Search
      • Introduction pdf
      • History and Definitions pdf
      • Agents pdf
      • Search pdf
      • Path-Finding pdf
      • Games pdf
      • Advanced Search pdf
      • Ethics, Legality & Society pdf
    • Reflection Preparation pdf
    • General Reflection Instructions pdf
    • Part 2: Multi-Agent Systems and Machine Learning
      • Multi-Agent Systems
        • Introduction to Machine Learning pdf
        • Game Theory and Social Welfare pdf
        • Making Collective Decisions pdf
      • Machine Learning
        • Definitions pdf
        • Unsupervised Learning - Clustering & Association Rule Mining pdf
        • Supervised Learning - Decision Trees and Random Forests pdf
        • Reinforcement Learning - Multi-Armed Bandit Problems pdf
    • Part 3: Neural Networks
      • Model Fitting pdf
      • Neural Networks pdf
      • Data pdf
      • SGD pdf
      • Convolutional Neural Networks pdf
      • Auto-Encoders pdf
      • Natural Language Processing pdf
      • Agentic AI

Technology

  • Python 3 (labs -> 3.13.11)
    We will not be using Python 3.14.X as it does not support tensorflow
    • Python 3.13.11 can be found Here
    • Most likely pick one of:
      • Visual Studio Code IDE Here
      • Pycharm IDE Here (Should be able to use ucalgary email to access Professional version as student)
    • Notebook Python solutions:
      • Google Colab: interactive notebooks for python here
      • Jupyter IPython Notebooks (can run these in Pycharm or otherwise install on your own system) Here

Quizzes/Participations

  • Quizzes
    • 6 times through-out semester
    • 20 minute online open book D2L quizzes.
    • Best 5 of 6 count.
  • Participations
    • 9 times through-out semester
    • Require in-person attendance in tutorials. May be required to be submitted end of tutorial or sometimes in D2L.
    • Best 8 of 9 count.

Discussion/Reflection

  • Discussion/Reflection 1
    • In-Class Date: Friday, February 6th, 2026 11:59(11:59 AM)
    • Submission of corresponding reflection to D2L by February 13th, 2026 23:59 (11:59 PM)
  • Discussion/Reflection 2
    • In-Class Date: Friday, March 13th, 2026 11:59 (11:59 AM)
    • Submission of corresponding reflection to D2L by March 20th, 2026 23:59 (11:59 PM)
  • Discussion/Reflection 3
    • In-Class Date: Friday, April 10th, 2026 11:59 (11:59 AM)
    • Submission of corresponding reflection to D2L by April 17th, 2026 23:59 (11:59 PM)

Aegis

Assignments

  • Assignment 1
    • Due Date: Friday, February 13th, 2026 23:59 (11:59 PM)
    • Description: Individual Assignment
    • Topics: Search/Path-Finding
    • Assignment Description
  • Assignment 2
    • Due Date: Friday, March 27th, 2026 23:59 (11:59 PM)
    • Description: Team Assignment
    • Topics: Mult-Agent Systems/Communication/Planning
    • Assignment Description
  • Assignment 3
    • Due Date: Tuesday, April 14th, 2026 23:59 (11:59 PM)
    • Description: Individual Assignment
    • Topics: Machine Learning/Image Recognition
    • Assignment Description
    • Dataset