2 What is AI Strong AI and Weak AI AI domains AI methods AI and other disciplinesTimeline
3 Strong AICreate a robot which is autonomous, thinks for itself, makes its own decisions, can deliberate about its own thoughts, can learn and adapt to new situations and can communicate with humans through the use of language
4 Weak AITo build a computer program that simulates a particular intelligent activity, e.g. playing chess
5 Some AI Definitions"The branch of computer science that is concerned with the automation of intelligent behavior.”" The science of making machines do things that would require intelligence if done by men.”"The study of computations that make it possible to perceive, reason, and act"
6 Some Important Questions How do we define human behavioral and thinking patternsHow do we define a rational behaviorWhat should be the difference between an ordinary program (say a sorting program) and an AI programWhat is the essence of intelligent behavior
7 Specifics of AI problems Require both procedural and declarative knowledgeRequire reasoning abilitiesRequire planningRequire learning abilities
8 Intelligent Agents Features Topics Goal - motivated behavior State space searchDecision makingLogical systems; reasoning patternsKnowledge-based behaviorKnowledge representationInformationDataKnowledgeAdaptive behaviorMachine learningInteraction and communicationVision, Pattern recognitionNatural Language ProcessingPhysical activityRobotics
9 AI methods, problems, applications Paradigms: Symbolic; ConnectionistsMethods: Knowledge Representation, Logic, SearchProblems: Planning and Decision Making, Pattern Recognition, Machine LearningApplications: Intelligent agents, Expert systems, Game playing, Natural Language Processing, Robotics
12 ExampleA farmer has to move a goat, a cabbage and a wolf from one side of a river to the other side using a small boat. The boat can carry only the farmer and one more object (either the goat, or the cabbage, or the wolf).If the farmer leaves the goat with the wolf alone, the wolf would kill the goat.If the goat is alone with the cabbage, it will eat the cabbage.How can the farmer move all his property safely to the other side of the river?
13 Solution Identify the initial and the target states Choose appropriate representation of the statesDecide on operators to change the states.Identify restrictions: are all operators applicable to all states?Decide on how the cost of the solution would be measuredSolve the problem
14 AI and other disciplines PhilosophyPsychology/ Cognitive psychology / Cognitive ScienceMathematicsComputer ScienceComputer EngineeringComputational LinguisticsBiology and Neurology
15 Timeline of AI1943 Warren McCulloch and Walter Pitts: a model of connected artificial neurons1956 Dartmouth workshop Alan Turing, John McCarthy, Marvin Minsky, Allen Newell1958 LISP by McCarthy
16 Timeline of AI1965 ELIZA :Weizenbaum, a program that acts as a psychoterapist.Work on machine translation - unsuccessful.1966 Funding for AI stopped.Difficulties: Lack of knowledge about world. The scale problem - easy to solve toy problems, very difficult to solve real world problems
17 Timeline of AI 1969-1979 Knowledge -based systems 1972 Prolog, created by Alain Colmerauer1975 Frames: a knowledge representation scheme, developed by Marvin Minsky.
18 Timeline of AISHRDLU by Terry Winograd - understanding natural language in the block worldDENDRAL - inferring molecular structure from the information provided by a mass spectrometer. Developed by Edward Feigenbaum
19 Timeline of AIMYCIN – a rule-based system for knowledge representation and inference in the domain of medical diagnosis and therapy.(The first expert system) .
20 Timeline of AI1980 R1 - first commercial ES - McDermott, configures orders for new computer systems.1981 Fifth generation project in Japan.Mid 80's Neural Networks
21 Timeline of AI1990’s Major advances in Machine learning, Natural language processing, multi-agent systems, robotics
22 Timeline of AI 2000 Robotics: Humanoid robots - Rodney Brook Robo-Cup soccerHumanoid sociable robotsInteractiverobot petsRoboCup Humanoid League 2006