COMS 4701, Artificial Intelligence

Artificial intelligence (AI) is a broad, interdisciplinary, and rapidly evolving field of computer science concerned with the design of systems that can perceive, reason, learn, and act. This course provides an overview of the fundamental methods and applications of AI, with an emphasis on algorithms, computation, and the evolution of the field from classical approaches to modern AI systems. Topics include search and planning, probabilistic reasoning, reinforcement learning, deep learning, foundation models, and agentic AI. Students will develop intuition and algorithmic thinking through written and programming problems in Python, and will apply these concepts to building and evaluating intelligent systems. By the end of the course, students will be able to formulate AI problems, reason and make decisions under uncertainty, learn from data, and design modern AI systems that use foundation models and other AI techniques.

Course Objectives

• Formulate and solve AI problems using state-space search.
• Model and solve adversarial and constraint-based problems using search and constraint satisfaction methods.
• Model and perform probabilistic inference in uncertain and sequential environments.
• Formulate sequential decision problems as Markov decision processes and apply dynamic programming and reinforcement learning methods.
• Apply fundamental machine learning methods to supervised learning problems.
• Explain and implement fundamental components of neural networks and deep learning.
• Explain the principles underlying transformers and foundation models.
• Design and evaluate modern AI systems.

Prerequisites

• Data structures and basic algorithms
• Programming experience, preferably in Python or a similar language
• Basic probability theory, including discrete probability distributions, conditional probability, independence, and Bayes’ rule
• Basic linear algebra, including vectors, matrices, matrix operations, and dot products
• Basic multivariable calculus (derivatives and gradients)

General List of Topics

1. Overview and foundations of AI
2. Intelligent agents
3. Best-first search
4. Local search and optimization
5. Constraint satisfaction problems
6. Games and adversarial search
7. Monte Carlo tree search
8. Probability and Bayesian networks
9. Sequential probabilistic models
10. Sampling-based inference
11. Sequential decision making
12. Dynamic programming
13. Tabular reinforcement learning
14. Function approximation
15. Policy search and actor-critic methods
16. Supervised learning methods
17. Linear classification
18. Neural networks
19. Spatial models and computer vision
20. Sequence modeling and self-attention
21. Foundation models and alignment
22. Multimodal models
23. Agentic AI systems
24. Evaluation, safety, and responsible AI