Course 1: Introduction to Artificial Intelligence Build a strong foundation in artificial intelligence by exploring core concepts from both a theoretical and practical perspective. This course blends essential principles with real-world problem-solving.6 hoursWelcome to Artificial IntelligenceWelcome to Introduction to Artificial Intelligence!Introduction to Artificial IntelligenceAn introduction to basic AI concepts and the challenge of answering "what is AI?"Solving Sudoku With AIIn this lesson, you'll dive right in and apply Artificial Intelligence to solve every Sudoku puzzle. Setting Up Your Environment and WorkspacesIf 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.Build a Sudoku SolverUse constraint propagation and search to build an agent that reasons like a human would to efficiently solve any Sudoku puzzle.Constraint Satisfaction ProblemsExpand 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.Course 2: Classical Search Learn classical graph search algorithms--including uninformed search techniques like breadth-first and depth-first search and informed search with heuristics including A*. These algorithms are at the heart of many classical AI techniques, and have been used for planning, optimization, problem solving, and more. Complete the lesson by teaching PacMan to search with these techniques to solve increasingly complex domains.4 hoursIntroductionPeter Norvig, co-author of _Artificial Intelligence: A Modern Approach_, explains a framework for search problems, and introduces uninformed & informed search strategies to solve them.Uninformed SearchPeter introduces uninformed search strategies—which can only solve problems by generating successor states and distinguishing between goal and non-goal states.Informed SearchPeter introduces informed search strategies, which means that they use problem-specific knowledge to find solutions more efficiently than an uninformed search.Classroom Exercise: SearchComplete a practice exercise where you'll implement informed and uninformed search strategies for the game PacMan.Additional Search TopicsReferences to additional readings on search.Course 3: Automated Planning Learn to represent general problem domains with symbolic logic and use search to find optimal plans for achieving your agent’s goals. Planning & scheduling systems power modern automation & logistics operations, and aerospace applications like the Hubble telescope & NASA Mars rovers.7 hoursSymbolic Logic & ReasoningPeter 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.Introduction to PlanningPeter 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.Classical PlanningPeter presents a survey of Classical Planning techniques: forward planning (progression search) & backward planning (regression search).Build a Forward-Planning AgentIn 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. Additional Planning TopicsPeter discusses plan space search & situational calculus. Finish the lesson with readings on advanced planning topics & modern applications of automated planning.Course 4: Optimization Problems Learn about iterative improvement optimization problems and classical algorithms emphasizing gradient-free methods for solving them. These techniques can often be used on intractable problems to find solutions that are "good enough" for practical purposes, and have been used extensively in fields like Operations Research & logistics. Finish the lessons by completing a classroom exercise comparing the different algorithms' performance on a variety of problems.4 hoursIntroductionThad 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.Hill ClimbingThad introduces _Hill Climbing_, a very simple local search optimization technique that works well on many iterative improvement problems.Simulated AnnealingThad explains _Simulated Annealing_, a classical global optimization technique for optimization.Genetic AlgorithmsThad introduces another optimization technique: _Genetic Algorithms_, which uses a population of samples to make iterative improvements towards the goal.Optimization ExerciseComplete a classroom exercise implementing simulated annealing to solve the traveling salesman problem.Additional Optimization TopicsReview similarities of the techniques introduced in this lesson with links to readings on advanced optimization topics, then complete an optimization exercise in the classroom.Course 5: Adversarial Search Learn how to search in multi-agent environments (including decision making in competitive environments) using the minimax theorem from game theory. Then build an agent that can play games better than any human.5 hoursIntroduction to Adversarial SearchExtend classical search to adversarial domains, to build agents that make good decisions without any human intervention—such as the DeepMind AlphaGo agent.Search in Multiagent DomainsSearch in multi-agent domains, using the Minimax theorem to solve adversarial problems and build agents that make better decisions than humans.Optimizing Minimax SearchSome of the limitations of minimax search and introduces optimizations & changes that make it practical in more complex domains.Build an Adversarial Game Playing AgentBuild agents that make good decisions without any human intervention—such as the DeepMind AlphaGo agent.Extending Minimax SearchExtensions to minimax search to support more than two players and non-deterministic domains.Additional Adversarial Search TopicsIntroduce Monte Carlo Tree Search, a highly-successful search technique in game domains, along with a reading list for other advanced adversarial search topics.Course 6: Fundamentals of Probabilistic Graphical Models Learn to use Bayes Nets to represent complex probability distributions, and algorithms for sampling from those distributions. Then learn the algorithms used to train, predict, and evaluate Hidden Markov Models for pattern recognition. HMMs have been used for gesture recognition in computer vision, gene sequence identification in bioinformatics, speech generation & part of speech tagging in natural language processing, and more.14 hoursIntroduction to Probabilistic ModelsWelcome to Fundamentals of Probabilistic Graphical Models. In this lesson, we will cover the course overview, prerequisites, and do a brief introduction to probability.ProbabilitySebastian Thrun briefly reviews basic probability theory including discrete distributions, independence, joint probabilities, and conditional distributions to model uncertainty in the real world.Spam Classifier with Naive BayesIn this section, you'll learn how to build a spam email classifier using the naive Bayes algorithm.Bayes NetsSebastian explains using Bayes Nets as a compact graphical model to encode probability distributions for efficient analysis.Inference in Bayes NetsSebastian explains probabilistic inference using Bayes Nets, i.e. how to use evidence to calculate probabilities from the network.Part of Speech Tagging with HMMsLearn Hidden Markov Models, and apply them to part-of-speech tagging, a very popular problem in Natural Language Processing.Dynamic Time WarpingThad explains the Dynamic Time Warping technique for working with time-series data.Project: Part of Speech TaggingIn this project, you'll build a hidden Markov model for part of speech tagging with a universal tagset.Course 7: After the AI Nanodegree Program Once you've completed the last project, review the information here to discover resources for you to continue learning and practicing AI. 15 minutesAdditional Topics in AISuggested resources to continue learning about artificial intelligence after completing the Nanodegree program.Course 8: OptionalExtracurricular OptionalAdditional lecture material on hidden Markov models and applications for gesture recognition.1 hourHidden Markov ModelsThad returns to discuss using Hidden Markov Models for pattern recognition with sequential data.Advanced HMMsThad shares advanced techniques that can improve performance of HMMs recognizing American Sign Language, and more complex HMM models for applications like speech synthesis.CompanyAbout UsWhy Udacity?BlogIn the NewsJobs at UdacityBecome a MentorPartner with UdacityResourcesCatalogCareer OutcomesHelp and FAQScholarshipsResource CenterFeatured ProgramsBusiness AnalyticsSQLAWS Cloud ArchitectData AnalystIntro to ProgrammingDigital MarketingSelf Driving Car EngineerOnly at UdacityArtificial IntelligenceDeep LearningDigital MarketingFlying Car and Autonomous Flight EngineerIntro to Self-Driving CarsMachine Learning EngineerRobotics Software EngineerAI Master’sMaster of Business AdministrationMaster of Science in AIUdacity SchoolsSchool of Animation and Game DevelopmentSchool of Artificial IntelligenceSchool of Autonomous SystemsSchool of BusinessCareer ResourcesSchool of Cloud ComputingSchool of CybersecuritySchool of Data ScienceSchool of DevOpsSchool of Executive LeadershipSchool of Product ManagementSchool of Programming and Development