Introduction to Artificial Intelligence
Jan 20, 2016
Introduction to
Artificial Intelligence
What is AI?What is AI?
How doesthe humanbrain work?
How do weemulate thehuman brain?
Who cares? Let’sdo some cool anduseful stuff!
How do wecreate
intelligence?What isintelligence?
How do we classify research as AI?How do we classify research as AI?
Does itinvestigatethe brain?
If we don’t know howit works, then it’s AI.When we find outhow it works, it’s notAI anymore…
Is itintelligent?Does it
investigateintelligence?
Does it emulatethe brain?
IntelligenceIntelligence The ability to learn and to cope.The ability to learn and to cope. The ability to contemplate, think, and The ability to contemplate, think, and
reason.reason. SynonymsSynonyms::
Brain, brainpower, mentality, mother wit, Brain, brainpower, mentality, mother wit, sense, witsense, wit
RelatedRelated:: Acumen, discernmentAcumen, discernment (ayırıcılık, duyarlılık) (ayırıcılık, duyarlılık), ,
insight, judgmentinsight, judgment (yargı) (yargı), perspicacity, sagacity, perspicacity, sagacity (sağduyu)(sağduyu), wisdom, wisdom (bilgelik) (bilgelik)
IntelligenceIntelligence Turing TestTuring Test: A human communicates with a : A human communicates with a
computer via a teletype. If the human can’t computer via a teletype. If the human can’t tell he is talking to a computer or another tell he is talking to a computer or another human, it passes.human, it passes. Natural language processingNatural language processing knowledge representationknowledge representation automated reasoningautomated reasoning machine learningmachine learning
Add vision and robotics to get the total Add vision and robotics to get the total Turing test.Turing test.
Weak and Strong AI ClaimsWeak and Strong AI Claims
Weak AI:Weak AI: Machines can be made to act Machines can be made to act as ifas if they were they were
intelligent.intelligent. Strong AI:Strong AI:
Machines that act intelligently have real, Machines that act intelligently have real, conscious minds.conscious minds.
Approaches to AIApproaches to AI
SearchingSearching LearningLearning From Natural to Artificial SystemsFrom Natural to Artificial Systems Knowledge Representation and ReasoningKnowledge Representation and Reasoning Expert Systems and PlanningExpert Systems and Planning Communication, Perception, ActionCommunication, Perception, Action
SearchSearch
““All AI is search”All AI is search” Game theoryGame theory Problem spacesProblem spaces
Every problem is a Every problem is a feature spacefeature space of all of all possible (successful or unsuccessful) possible (successful or unsuccessful) solutions.solutions.
The trick is to find an efficient search The trick is to find an efficient search strategy.strategy.
Search: Game TheorySearch: Game Theory
9!+1 = 362,880
Approaches to AIApproaches to AI
SearchingSearching LearningLearning From Natural to Artificial SystemsFrom Natural to Artificial Systems Knowledge Representation and ReasoningKnowledge Representation and Reasoning Expert Systems and PlanningExpert Systems and Planning Communication, Perception, ActionCommunication, Perception, Action
LearningLearning
ExplanationExplanation Discovery Discovery Data MiningData Mining
No ExplanationNo Explanation Neural NetsNeural Nets Case Based ReasoningCase Based Reasoning
Learning: ExplanationLearning: Explanation
Cases to rulesCases to rules
Learning: No ExplanationLearning: No Explanation
Neural netsNeural nets
Approaches to AIApproaches to AI
SearchingSearching LearningLearning From Natural to Artificial SystemsFrom Natural to Artificial Systems Knowledge Representation and ReasoningKnowledge Representation and Reasoning Expert Systems and PlanningExpert Systems and Planning Communication, Perception, ActionCommunication, Perception, Action
Approaches to AIApproaches to AI
SearchingSearching LearningLearning From Natural to Artificial SystemsFrom Natural to Artificial Systems Knowledge Representation and ReasoningKnowledge Representation and Reasoning Expert Systems and PlanningExpert Systems and Planning Communication, Perception, ActionCommunication, Perception, Action
Rule-Based SystemsRule-Based Systems
Logic LanguagesLogic Languages Prolog, LispProlog, Lisp
Knowledge basesKnowledge bases Inference enginesInference engines
Rule-Based Languages: PrologRule-Based Languages: Prolog
Father(abraham, isaac). Male(isaac).Father(haran, lot). Male(lot).Father(haran, milcah). Female(milcah).Father(haran, yiscah). Female(yiscah).
Son(X,Y) Father(Y,X), Male(X).Daughter(X,Y) Father(Y,X), Female(X).
Son(lot, haran)?
RuleBasedSystems
RuleBasedSystems
KRSKRS
Approaches to AIApproaches to AI
SearchingSearching LearningLearning From Natural to Artificial SystemsFrom Natural to Artificial Systems Knowledge Representation and ReasoningKnowledge Representation and Reasoning Expert Systems and PlanningExpert Systems and Planning Communication, Perception, ActionCommunication, Perception, Action
Approaches to AIApproaches to AI
SearchingSearching LearningLearning From Natural to Artificial SystemsFrom Natural to Artificial Systems Knowledge Representation and ReasoningKnowledge Representation and Reasoning Expert Systems and PlanningExpert Systems and Planning Communication, Perception, ActionCommunication, Perception, Action
Ability-Based AreasAbility-Based Areas Computer visionComputer vision Natural language recognitionNatural language recognition Natural language generationNatural language generation Speech recognitionSpeech recognition Speech generationSpeech generation RoboticsRobotics
Natural Language: TranslationNatural Language: Translation
“The flesh is weak, but the spirit is strong”
Translate to Russian Translate back to English
“The food was lousy, but the vodka was great!”
Natural Language RecognitionNatural Language Recognition
You give me the gold
pronounn
verb pronound
article noun
VP NP
VP
NP
VP
NP
sentencew
PERSON:Joe
PERSON:FredTRANSACTION
GOLD: X
REPT
OBJ
AGNT
Audio
Words
Syntax
Context
Semantics
Face Recognition ExampleFace Recognition Example
Take three regular photos from different Take three regular photos from different sides of a human facesides of a human face
Generate a digital model of the human faceGenerate a digital model of the human face Uses of the work:Uses of the work:
Medical applications: Aesthetic operationsMedical applications: Aesthetic operations Hair dresser and friseur worksHair dresser and friseur works Animations to use in movie industryAnimations to use in movie industry Etc.Etc.
ResultsResults
ResultsResults
ResultsResults
How far have we got?How far have we got?
Our best systems have the intelligence of a Our best systems have the intelligence of a frogfrog
What is Artificial Intelligence?What is Artificial Intelligence?
We will find out …We will find out …
Interesting webpagesInteresting webpages
http://aima.cs.berkeley.edu/demos.htmlhttp://aima.cs.berkeley.edu/demos.html http://lslwww.epfl.ch/~anperez/BlackJack/http://lslwww.epfl.ch/~anperez/BlackJack/
classes/RLJavaBJ.htmlclasses/RLJavaBJ.html