Course Objective:

This course introduces students to the fundamental concepts and algorithms of modern AI and Machine Learning. Topics include AI searching, classification, optimization, reinforcement learning, machine learning, and natural language processing.
Through projects, students will have an opportunity to explore key concepts and algorithms at the foundation of modern AI, including things behind technologies like game-engines, handwriting recognition, machine translation. Students will gain hands-on exposure to libraries for machine learning in Python, and acquire the knowledge to design intelligent systems of their own.

Learning Outcomes:

• Understand and apply foundational principles of artificial intelligence (AI) and machine learning.
• Implement graph search algorithms (such as BFS, DFS, A* search, and Greedy Search) for problem solving.
• Represent knowledge and reason under uncertainty: use logic, probabilistic models, Bayesian networks, Hidden Markov Models, etc., to model and solve real-world problems.
• Employ optimization techniques (constraint satisfaction, local search, linear programming) to improve AI-driven decision making.
• Build and apply machine-learning models: supervised learning (classification/regression), unsupervised learning (clustering), reinforcement learning.
• Understand neural networks and deep learning basics: architectures, training (backpropagation, gradient descent), and apply them (e.g., convolutional networks for image recognition).
• Work with natural language processing and language models: tokenization, word representations, n-grams, transformers/attention models.

Required Textbooks and Software Development Tools

1. Java, using Eclipse.
2. Python (3.11), using Visual Studio Code
3. Poole and Mackworth AI: Foundations of Computational Agents, Edition 2, 2023 Cambridge University Press
4. Cay Horstmann Python for Everyone, Edition 2, 2017 Wiley

Evaluation:

Quizzes: 50%
Homework: 50%




NOTE:

Canvas is used solely as a repository for your submitted work.
Canvas should not be treated as gradesheet for the course.

I. Quizzes

Short quizzes will be given about every two weeks during the semester.

II. Homework and Self-Grading

A set of programs will be assigned almost every week.
These assignments are be available on Canvas.



• Homework Assignments due date

  Place your name prominently as a comment at the top of each program.
  Format your code and include clear explanations as comments.
  All program must be tested, readible, and written efficienly.
  Late homework will not be accepted.

  ---

• Assignment Solutions and Do-overs

  Solutions to assigned programs will be posted to Canvas.
  Students are expected to explore these solutions to gain a better understanding of concepts.
  After examining the posted solutions, you may correct and resubmit your homework (via Canvas).

  Do NOT copy code from other students, other sources, or from posted solutions. You are encouraged to clarify concepts and discuss possible approaches with other students in the class. The objective is always to learn the concepts.

  ---

• Self-Grading Responsibilities

  Students are responsible for grading their own homework.
  Students will be asked to fully test their programs and check their execution results.
  An honor system will be used in all homework assignment to aid students in developing strong programming skills.
  The following Self-Grades Options should be entered into Canvas "do-over" for each assignment.
  
  Excellent Student explored, experimented, and fully solved the assignment using well-written code.
  Good Student satisfied the assignment. Work was good, but could have been better.
  Average Student satisfied the assignment, but with problems.
  Poor Student turned in incomplete or poorly executed work.
  
  




Grading Scale:

100 - 93% 92-90% 89-87% 86-83%

4.0 3.7 3.3 3.0

82-80% 79-77% 76-73% 72-70%

2.7 2.3 2.0 1.7

69-67% 66-63% 62-60% below 60%

1.3 1.0 0.7 0.0




---






Policies:

• Normal university policies concerning incomplete, etc.
• Make-up for tests requires either 2 weeks of advance notice (in case of planned absence), or a medical statement (in case of unforeseen problem).
• Credit will not be given to homework assignments turned in late.
• With the exception of one homework assignment, no extra credit work will be given during the semester. The extra credit for the one homework assignment will only be applied to homework grades of less than 100%.
• Any academic dishonesty will result in a failing grade.
• If a student has a disability that qualified for accommodations under the Americans with Disabilities Act and Section 504 of the Rehabilitation Act, she/she/they should contact Academic Success & Disability Services (ASDS). ASDS is located on the ground floor of the Armacost Library across from Human Resources and down the hall from the Jones Computer Center; their phone is 909-748-8069. The primary contact person is Amy Wilms.