Course Description

Artificial Intelligence (AI) influences numerous aspects of our lives, shaping how we live, work, and engage with entertainment. It drives advancements in cutting-edge technologies like autonomous vehicles and recommendation systems while enhancing existing solutions such as medical diagnostics and search engines. As the demand for AI and machine learning expertise grows, this course serves as a gateway to addressing real-world challenges and preparing for a future in this transformative field.

In this course, we will explore the foundational concepts and algorithms underpinning modern AI. Topics include robotics, automated planning, algorithmic game theory, probabilistic inference, and machine learning. Through hands-on projects, students will apply theories related to graph search algorithms, classification, optimization, reinforcement learning, and more. Practical experience will be gained through Python programming, enabling participants to design and implement intelligent systems. By the end of the course, students will have a solid understanding of AI principles and be equipped to tackle diverse problems in the field.

Learning Outcomes

By the end of this course, students will be able to:

  • Develop autonomous agents capable of making effective decisions in fully informed, partially observable, and adversarial settings.
  • Build agents that can draw inferences in uncertain environments and optimize actions based on varying reward structures.
  • Implement machine learning algorithms to classify handwritten digits and photographs.
  • Apply acquired knowledge to solve a broad range of artificial intelligence problems.
  • Establish a strong foundation for advanced study in any application area within artificial intelligence.

Expected Background Knowledge

Students are expected to be familiar with the following topics:

  • Proficiency in Python. Class assignments will require Python coding. For those needing a refresher, follow this Python tutorial. Complete all topics under "Python Tutorial," "Python NumPy," and "Machine Learning."
  • College-Level Calculus and Linear Algebra. Students should be comfortable with derivatives, matrix operations, and notation. Review the "Essence of Linear Algebra" and "Essence of Calculus" playlists by 3Blue1Brown.
  • Basic Probability and Statistics. Familiarity with probabilities, Gaussian, Beta, and Binomial distributions, as well as concepts like mean and standard deviation, is expected. Review the "Probabilities of Probabilities" playlist by 3Blue1Brown.
  • Foundations of Machine Learning. Students will work with loss functions, derivatives, and gradient descent optimization. Background knowledge in convex optimization and machine learning concepts is helpful.
  • Recommended Background Courses. CSCE 110 Programming, MATH 304 Linear Algebra, MATH 308 Differential Equations, MATH 411 Mathematical Probability.

Staff

Instructor Guni Sharon
E-Mail guni@tamu.edu
Office Hours Tuesday, 14:00 -- 15:00
Office PETR 316
TA Vaibhav Bajaj
E-Mail vaibhavbajaj@tamu.edu
Office Hours Wednesday, 16:30 -- 17:30
Office EAB-C 107B