Learn AI and master essential concepts from Optimization & Planning to Adversarial Search.
Classes start in
Study 12-15 hrs/week and complete in 3 months.
Learn from the world’s foremost AI experts, and develop a deep understanding of algorithms being applied to real-world problems in natural language processing, computer vision, bioinformatics, and more. Practice a structured approach for applying these techniques to new challenges, and emerge fully prepared to advance in the field.
Learn everything you need to start building your own AI applications
Learn AI algorithms that have been successfully applied to real world problems in NLP, computer vision, bioinformatics, and more. Learn how to solve problems with these tools so that you can apply them in the real world.
Explore probabilistic models for pattern recognition with Sebastian Thrun, founder of Google’s self-driving car team. Discover how to implement key AI algorithms with Peter Norvig, co-author of the leading AI textbook. Learn how to frame and solve modern AI problems, and gain real-world experience.
Engage with a mentor consistently throughout your program experience. As you build your AI skills, the mentor will provide 1:1 support as you master new concepts and complete challenging projects.
Work on career-caliber projects that will populate and enhance your professional profile, and benefit from detailed and actionable feedback from project reviewers who will help ensure you're doing your best work.
See fewer details
This program requires experience with linear algebra, statistics, and Python (including object-oriented programming).
Use constraint propagation and search to build an agent that reasons like a human would to efficiently solve any Sudoku puzzle.Build a Sudoku Solver
Build agents that can reason to achieve their goals using search and symbolic logic—like the NASA Mars rovers.Build a Forward Planning Agent
Extend classical search to adversarial domains, to build agents that make good decisions without any human intervention—such as the DeepMind AlphaGo agent.Build an Adversarial Game Playing Agent
Model real-world uncertainty through probability to perform pattern recognition.Part of Speech Tagging
Research Director, Google
Peter Norvig is a Director of Research at Google and is co-author of Artificial Intelligence: A Modern Approach, the leading textbook in the field.
Sebastian Thrun is a scientist, educator, inventor, and entrepreneur. Prior to founding Udacity, he launched Google’s self-driving car project.
Professor of Computer Science, Georgia Tech
Thad Starner is the director of the Contextual Computing Group (CCG) at Georgia Tech and is also the longest-serving Technical Lead/Manager on Google's Glass project.
Basic shell scripting:
Basic statistical knowledge, including:
Intermediate differential calculus and linear algebra, including:
Additionally, you should be able to follow and interpret pseudocode for algorithms like the example below and implement them in Python. You should also be able to informally evaluate the time or space complexity of an algorithm. For example, you should be able to explain that a for loop that does constant O(1) work on each iteration over an array of length n has a complexity of O(n).function Hill-Climbing(problem) returns a State current <- Make-Node(problem.Initial-State) loop do neighbor <- a highest-valued successor of current if neighbor.value ≤ current.value then return current.state current <- neighbor
We have a number of courses and programs we can recommend that will help prepare you for the program, depending on the areas you need to address. For example: