1 Artificial Intelligence Rob Kremer Department of Computer Science University of Calgary

2 What is AI?

3 How do we classify research as AI?

4 Approaches to AI n Learning n Rule-Based Systems n Search n Planning n Ability-Based Areas n Robotics n Agents

5 Learning n Explanation –Discovery –Data Mining n No Explanation –Neural Nets –Case Based Reasoning

6 Learning: Explanation n Cases to rules

7 Learning: No Explanation n Neural nets

8 Approaches to AI n Learning n Rule-Based Systems n Search n Planning n Ability-Based Areas n Robotics n Agents

9 Rule-Based Systems n Logic Languages –Prolog, Lisp n Knowledge bases n Inference engines

10 Rule-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)?

11 Rule Based Systems n KRS

12 Approaches to AI n Learning n Rule-Based Systems n Search n Planning n Ability-Based Areas n Robotics n Agents

13 Search n “All AI is search” –Game theory –Problem spaces n Every problem is a “virtual” tree of all possible (successful or unsuccessful) solutions. n The trick is to find an efficient search strategy.

14 Search: Game Theory 9!+1 = 362,880

15 Approaches to AI n Learning n Rule-Based Systems n Search n Planning n Ability-Based Areas n Robotics n Agents

16 Approaches to AI n Learning n Rule-Based Systems n Search n Planning n Ability-Based Areas n Robotics n Agents

17 Ability-Based Areas n Computer vision n Natural language recognition n Natural language generation n Speech recognition n Speech generation n Robotics

18 Natural Language: Translation “The spirit is strong, but the flesh is weak.”  Translate to Russian  Translate back to English “The vodka is great, but the meat is rancid!”

19 Natural Language Recognition

20 Natural Language Recognition “Tom believes Mary wants to marry a sailor.”

21 Approaches to AI n Learning n Rule-Based Systems n Search n Planning n Ability-Based Areas n Robotics n Agents RoboCup ChallengeRoboCup Game

22 Approaches to AI n Learning n Rule-Based Systems n Search n Planning n Ability-Based Areas n Robotics n Agents

23 Agent Communication Alice Bob (performative: request, content: attend(Bob,x)) Can you attend this meeting? (performative: agree, content: attend(Bob,x)) Sure... (performative: inform, content: attend(Bob,x)) I’m here (performative: confirm, content: attend(Bob,x)) Thanks for coming. (performative: ack, content: attend(Bob,x)) (nod) (performative: ack, content: attend(Bob,x)) (nod) (performative: ack, content: attend(Bob,x)) (nod)

24 Agent Communication reply-propose-discharge(Alice,Bob,x) act(Bob,Alice,x) propose-discharge(Bob,Alice,x) Alice Bob request inform reply agree informack propose-discharge done reply informack reply-propose-discharge confirm reply informack reply(Bob,Alice,x) ack(Bob,Alice,x) ack ack(Bob,Alice,x) ack ack(Alice,Bob,x) ack ack(Alice,Bob,x) ack

25 Intelligence n Turing Test: A human communicates with a computer via a teletype. If the human can’t tell he is talking to a computer or another human, it passes. –Natural language processing –knowledge representation –automated reasoning –machine learning n Add vision and robotics to get the total Turing test.

26 Weak and Strong AI Claims n Weak AI: –Machines can be made to act as if they were intelligent. n Strong AI: –Machines that act intelligently have real, conscious minds.

27 What is Intelligence? n The Chinese Room

28 What is Intelligence? n The Chinese Room

29 What is Intelligence? n Replacing the brain

30 How far have we got? n Our best systems have the intelligence of a frog n Mind you, how many frogs spend all their intelligence controlling a nuclear power plant?