Course Content
Module 1: Introduction
What Is AI?
The Foundations of Artificial Intelligence
TheHistoryofArtificialIntelligence
TheStateoftheArt
Risks and Benefits of AI
Module 2:
Intelligent Agents
AgentsandEnvironments
Good Behavior:TheConceptofRationality
The Nature of Environments
The Structure of Agents
Module 4: Solving Problems by Searching
Problem-Solving Agents
Example Problems
Search Algorithms
UninformedSearchStrategies
Informed(Heuristic)SearchStrategies
HeuristicFunctions
Module 4
Search in Complex Environments
LocalSearchandOptimizationProblems
LocalSearchinContinuousSpaces
SearchwithNondeterministicActions
Searching Partially Observable Environments
Online Search Agents and Unknown Environments
Module 5
Adversarial Search and Games
GameTheory
OptimalDecisionsinGames
HeuristicAlpha–BetaTreeSearch
MonteCarloTreeSearch
StochasticGames
PartiallyObservableGames
LimitationsofGameSearchAlgorithms
Module 6
Constraint Satisfaction Problems
DefiningConstraintSatisfactionProblems
ConstraintPropagation:InferenceinCSPs
BacktrackingSearchforCSPs
LocalSearchforCSPs
TheStructureofProblems
Module 7
Logical Agents 208
Knowledge-BasedAgents
TheWumpusWorld
Logic
PropositionalLogic:AVerySimpleLogic
PropositionalTheoremProving
EffectivePropositionalModelChecking
AgentsBasedonPropositionalLogic
Module 8
First-Order Logic
RepresentationRevisited
SyntaxandSemanticsofFirst-OrderLogic
UsingFirst-OrderLogic
KnowledgeEngineeringinFirst-OrderLogic
Module 9
Inference in First-Order Logic
Propositionalvs.First-OrderInference
UnificationandFirst-OrderInference
ForwardChaining
BackwardChaining
Resolution
Module 10
Knowledge Representation
OntologicalEngineering
CategoriesandObjects
Events
MentalObjectsandModalLogic
ReasoningSystemsforCategories
ReasoningwithDefaultInformation
Module 11
Automated Planning
DefinitionofClassicalPlanning
AlgorithmsforClassicalPlanning
HeuristicsforPlanning
HierarchicalPlanning
Planning and Acting in Nondeterministic Domains
Time,Schedules,andResources
AnalysisofPlanningApproaches
Module 12
Quantifying Uncertainty
ActingunderUncertainty
BasicProbabilityNotation
InferenceUsingFullJointDistributions
Independence
Bayes’RuleandItsUse
NaiveBayesModels
TheWumpusWorldRevisited
Module 13
Probabilistic Reasoning
RepresentingKnowledgeinanUncertainDomain
TheSemanticsofBayesianNetworks
ExactInferenceinBayesianNetworks
ApproximateInferenceforBayesianNetworks
CausalNetworks
Module 14
Probabilistic Reasoning over Time
TimeandUncertainty
InferenceinTemporalModel
HiddenMarkovModels
KalmanFilters
DynamicBayesianNetworks
Module 15
Probabilistic Programming
RelationalProbabilityModels
UniverseProbabilityModels
KeepingTrackofaComplexWorld
ProgramsasProbabilityModels
Module 16
Making Simple Decisions
Combining Beliefs and Desires under Uncertainty
TheBasisofUtilityTheory
UtilityFunctions
MultiattributeUtilityFunctions
DecisionNetworks
TheValueofInformation
UnknownPreferences
Module 17
Making Complex Decisions
SequentialDecisionProblems
AlgorithmsforMDPs
BanditProblems
PartiallyObservableMDPs
AlgorithmsforSolvingPOMDPs
Module 18
Multiagent Decision Making 599
PropertiesofMultiagentEnvironments
Non-CooperativeGameTheory
CooperativeGameTheory
MakingCollectiveDecisions
Module 19
Learning from Examples
FormsofLearning
SupervisedLearning
LearningDecisionTrees
ModelSelectionandOptimization
TheTheoryofLearning
LinearRegressionandClassification
NonparametricModels
EnsembleLearning
DevelopingMachineLearningSystems
Module 20
Learning Probabilistic Models
StatisticalLearning
LearningwithCompleteData
LearningwithHiddenVariables:TheEMAlgorithm
Module 21
Deep Learning
SimpleFeedforwardNetworks
ComputationGraphsforDeepLearning
ConvolutionalNetworks
LearningAlgorithms
Generalization
RecurrentNeuralNetworks
UnsupervisedLearningandTransferLearning
Applicationsy
Module 22
Reinforcement Learning
LearningfromRewards
PassiveReinforcementLearning
ActiveReinforcementLearning
GeneralizationinReinforcementLearning
PolicySearch
Apprenticeship and Inverse Reinforcement Learning
ApplicationsofReinforcementLearning
Module 23
Natural Language Processing
LanguageModels
Grammar
Parsing
AugmentedGrammars
ComplicationsofRealNaturalLanguage
NaturalLanguageTasks
Module 24
Deep Learning for Natural Language Processing
WordEmbeddings
RecurrentNeuralNetworksforNLP
Sequence-to-SequenceModels
TheTransformerArchitecture
PretrainingandTransferLearning
Stateoftheart
Module 25
Computer Vision
Introduction
ImageFormation
SimpleImageFeatures
ClassifyingImages
DetectingObjects
The3DWorld
UsingComputerVision
Module 26
Robotics
Robots
RobotHardware
Whatkindofproblemisroboticssolving?
RoboticPerception
PlanningandControl
PlanningUncertainMovements
ReinforcementLearninginRobotics
HumansandRobots
AlternativeRoboticFrameworks
ApplicationDomains
Module 27
Philosophy, Ethics, and Safety of AI
TheLimitsofAI
CanMachinesReallyThink?
TheEthicsofAI
Module 28
The Future of AI
AIComponents
AIArchitectures