Artificial Intelligence Nanodegree

Welcome to the Artificial Intelligence Nanodegree program!

You are starting a challenging but rewarding journey! Take 5 minutes to read how to get help with projects and content.

What to do if you have questions about your account or general questions about the program.

An introduction to basic AI concepts and the challenge of answering "what is AI?"

In this lesson, you'll dive right in and apply Artificial Intelligence to solve every Sudoku puzzle.

Review the basic functionality of Workspaces—pre-configured development environments in the Udacity classroom for projects and exercises.

If you do not want to use Workspaces, then follow these instructions to set up your own system using Anaconda, a popular tool to manage your environments and packages in python.

Use constraint propagation and search to build an agent that reasons like a human would to efficiently solve any Sudoku puzzle.

Project Description - Build a Sudoku Solver

Project Rubric - Build a Sudoku Solver

Learn about common jobs in artificial intelligence, and get tips on how to stay active in the community.

Other professionals are collaborating on GitHub and growing their network. Submit your profile to ensure your profile is on par with leaders in your field.

Project Description - Optimize Your GitHub Profile

Project Rubric - Optimize Your GitHub Profile

Expand from the constraint propagation technique used in the Sudoku project to the Constraint Satisfaction Problem framework that can be used to solve a wide range of general problems.

Practice formulating some classical example problems as CSPs, and then to explore using a powerful open source constraint satisfaction tool called Z3 from Microsoft Research to solve them.

Reading list of applications and additional topics related to CSPs.

Peter Norvig, co-author of Artificial Intelligence: A Modern Approach, explains a framework for search problems, and introduces uninformed & informed search strategies to solve them.

Peter introduces uninformed search strategies—which can only solve problems by generating successor states and distinguishing between goal and non-goal states.

Peter introduces informed search strategies, which means that they use problem-specific knowledge to find solutions more efficiently than uninformed search.

Complete a practice exercise where you'll implement informed and uninformed search strategies for the game PacMan.

References to additional readings on search.

Peter Norvig returns to explain propositional logic and first-order logic, which provide a symbolic logic framework that enables AI agents to reason about their actions.

Peter Norvig defines automated planning problems in comparison to more general problem solving techniques to set the stage for classical planning algorithms in the next lesson.

Peter presents a survey of Classical Planning techniques: forward planning (progression search) & backward planning (regression search).

In this project you’ll use experiment with search and symbolic logic to build an agent that automatically develops and executes plans to achieve their goals.

Project Description - Build a Forward-Planning Agent

Project Rubric - Build a Forward-Planning Agent

Peter discusses plan space search & situational calculus. Finish the lesson with readings on advanced planning topics & modern applications of automated planning.

Thad Starner introduces the concept of iterative improvement problems, a class of optimization problems that can be solved with global optimization or local search techniques covered in this lesson.

Thad introduces Hill Climbing, a very simple local search optimization technique that works well on many iterative improvement problems.

Thad explains Simulated Annealing, a classical global optimization technique for optimization.

Thad introduces another optimization technique: Genetic Algorithms, which uses a population of samples to make iterative improvements towards the goal.

Complete a classroom exercise implementing simulated annealing to solve the traveling salesman problem.

Review similarities of the techniques introduced in this lesson with links to readings on advanced optimization topics, then complete an optimization exercise in the classroom.

Thad returns to teach search in multi-agent domains, using the Minimax theorem to solve adversarial problems and build agents that make better decisions than humans.

Thad explains some of the limitations of minimax search and introduces optimizations & changes that make it practical in more complex domains.

Extend classical search to adversarial domains, to build agents that make good decisions without any human intervention—such as the DeepMind AlphaGo agent.

Project Description - Build an Adversarial Game Playing Agent

Project Rubric - Build an Adversarial Game Playing Agent

Thad introduces extensions to minimax search to support more than two players and non-deterministic domains.

Introduce Monte Carlo Tree Search, a highly-successful search technique in game domains, along with a reading list for other advanced adversarial search topics.

Find your next job or connect with industry peers on LinkedIn. Ensure your profile attracts relevant leads that will grow your professional network.

Project Description - Improve Your LinkedIn Profile

Project Rubric - Improve Your LinkedIn Profile

Sebastian Thrun briefly reviews basic probability theory including discrete distributions, independence, joint probabilities, and conditional distributions to model uncertainty in the real world.

In this section, you'll learn how to build a spam e-mail classifier using the naive Bayes algorithm.

Sebastian explains using Bayes Nets as a compact graphical model to encode probability distributions for efficient analysis.

Sebastian explains probabilistic inference using Bayes Nets, i.e. how to use evidence to calculate probabilities from the network.

Learn Hidden Markov Models, and apply them to part-of-speech tagging, a very popular problem in Natural Language Processing.

In this project you will build a hidden Markov model (HMM) to perform part of speech tagging, a common pre-processing step in Natural Language Processing.

Project Description - Part of Speech Tagging

Project Rubric - Part of Speech Tagging

Thad explains the Dynamic Time Warping technique for working with time-series data.

Reading list of select topics to continue learning about probabilistic graphical models.

Suggested resources to continue learning about artificial intelligence after completing the Nanodegree program.

Thad returns to discuss using Hidden Markov Models for pattern recognition with sequential data.

Thad shares advanced techniques that can improve performance of HMMs recognizing American Sign Language, and more complex HMM models for applications like speech synthesis.