Mar 13, 2025  
2023-2024 Undergraduate Academic Catalog-June Update 
    
2023-2024 Undergraduate Academic Catalog-June Update [ARCHIVED CATALOG]

Add to Portfolio (opens a new window)

BUS 3850 - Topics in Artificial Intelligence

3 lecture hours 0 lab hours 3 credits
Course Description
This course introduces the basic concepts of Artificial Intelligence (AI) in a manner designed to attract newcomers to the field who are curious about AI. Tools, techniques, and devices from laboratories in the Diercks Hall Center for Artificial Intelligence will be used to develop solutions using machine learning, computer vision, and natural language processing technologies pioneered by AI practitioners. Students will experiment with various technologies common in the field of AI to address problems across multiple engineering and business disciplines. (prereq: none)
Course Learning Outcomes
Upon successful completion of this course, the student will be able to:
  • Demonstrate an understanding of the principles of formal logic, including propositional and first order logic, inference, rule-based deduction, and resolution
  • Solve problems using search techniques such as depth-first, breadth-first, forward chaining, backward chaining, heuristic search, and adversarial search
  • Understand game theory and game-playing strategies using AI, such as Minimax search, alpha-beta pruning, and back propagation of errors
  • Use tools and techniques common in AI for discovery, including Jupyter Notebooks, the Python programming language, and neural network frameworks such as Keras, PyTorch, and TensorFlow
  • Understand the application of machine learning and deep neural networks to discovery of new knowledge and information

Prerequisites by Topic
  • None

Course Topics
  • Introduction to AI
  • History and milestones in AI systems
  • Knowledge representation
    • Rules, objects, algorithms, networks, simulations
      • Production systems, forward and backward chaining, certainty factors
      • Formal logic, clausal form, resolution
  • Search
    • Defining the search space
      • Trees, decision trees, game trees, graphs
    • Search algorithms
      • Breadth-first, depth-first and uniform cost search
    • Adversarial search
      • Minimax, A*, α-β pruning, shortest path algorithms
  • Python and Jupyter Notebook basics
  • Python programming language essentials
    • Expressions, operators, functions, lambdas
    • Objects, lists, tuples, dictionaries, sets
    • Libraries used in AI and data science
      • NumPy, SciPy, Pandas, SciKit Learn, Keras, PyTorch, TensorFlow
  • Machine Learning
    • Supervised learning
      • Regression methods, classification methods
    • Unsupervised learning
      • Clustering methods
  • Deep learning
    • Neural networks
      • Perceptrons, feed forward and back propagation algorithms, cost functions, error surfaces, gradient descent
    • Convolutional and recurrent neural networks,
  • Applications of AI
    • Game theory
    • Computer vision (image processing)
    • Natural language processing

Coordinator
Dr. Michael Payne



Add to Portfolio (opens a new window)