CS 335 – Introduction to Artificial Intelligence

This course covers strong artificial intelligence methods, which have resulted in the development of systems that solve open problems in specialized domains. Such methods include 1) AI models based on logical reasoning, in particular decision trees and learning decision trees, rule-based expert systems, semantic nets, and frames; 2) AI models based on probabilistic reasoning, in particular Bayesian networks and learning Bayesian networks, influence diagrams, and class probability trees; and 3) AI models based on emergent intelligence, in particular evolutionary computation and swarm intelligence. Lastly, the course discusses an important endeavor in AI, namely, language processing.

Lush gradients and nodes capturing AI curiosity for summer cohorts.

Course stats

Course rating
4.9 / 5
Recommendation
96% would recommend
Instructor rating
4.9 / 5

Experience pulse

  • Instructor Available for Help4.9 / 5
  • Intellectually Challenging4.4 / 5
  • I Learned a Lot4.8 / 5

Student reviews

  • Summer 2025

    The AI chatbot project was amazing, I gained hands-on experience training and deploying a model.

  • Summer 2025

    Professor Omeed’s teaching style helped me thoroughly understand each topic.

Logistics

Semester
Summer 2025
Meeting times
Tuesdays & Thursdays @ 11:00 AM - 12:50 PM (LWH 3003)
Office hours
Fridays @ 12:00 PM - 12:30 PM CST (Virtual) or by appointment
View syllabus →

Major course topics

  • Introduction to Artificial Intelligence (AI)
  • Python Programming for AI
  • Expert Systems
  • Search and Problem Solving
  • Machine Learning Fundamentals
  • Natural Language Processing (NLP)
  • Bayesian Inference and Probability
  • Semantic Search and Vector Embeddings
  • Retrieval-Augmented Generation (RAG)
  • AI Ethics and Real-World Considerations

What to expect

  • You will be able to understand what artificial intelligence (AI) is, including its history, core concepts, and modern applications.
  • You can apply machine learning concepts such as supervised learning, training vs. testing data, and model evaluation.
  • You can perform basic natural language processing (NLP) tasks, including tokenization, sentiment analysis, and text classification.
  • Using the Retrieval-Augmented Generation (RAG) framework, you can build a chatbot that integrates information retrieval with text generation.
  • You can collaborate with others using version control tools like GitHub and follow development best practices in AI projects.

Preview material