1 of 45 artificial intelligence is 340 chandra s. amaravadi
TRANSCRIPT
11 of 45 of 45
ARTIFICIAL INTELLIGENCE
IS 340
CHANDRA S. AMARAVADI
22 of 45 of 45
ARTIFICIAL INTELLIGENCE
IN THIS PRESENTATION
Introduction to AI Milestones & early work Machine Intelligence
The Nature of knowledgeKnowledge representationExamplesNeural nets Business & recent applications
33 of 45 of 45
INTRODUCTION TO AI
44 of 45 of 45
THE HISTORY OF AI (FYI)
•Alan Turing & test for intelligence -- 1950•AI as a field of study -- 1956•Lisp language -- 1958•Expert Systems -- 1965
•Dendral & Mycin•Small Talk, Prolog -- 1972•Fifth Generation Project -- 1981•Honda robot -- 1995•Stanford driverless car -- 2005
Major milestones
55 of 45 of 45
Early research on AI focussed on:
LogicPerceptronsChessBlocks world (a world consisting of only blocks)
EARLY RESEARCH
66 of 45 of 45
Generate and TestGenerate a possible solutionand test to see if it is the answer
Breadth-first Depth-first Heuristic Hill-climbing
SEARCH STRATEGIES
?
??
77 of 45 of 45
DEFINING INTELLIGENCE
88 of 45 of 45
Artificial Intelligence (AI)
DEFINITION
AI is concerned with the principles and mechanisms for achieving intelligent behavior in machines
99 of 45 of 45
Artificialintelligence
Robotics
NLP VisionSystems
MachineLearning
ExpertSystems
BRANCHES OF AI
1010 of 45 of 45
NATURE OF INTELLIGENCE
Knowledge + Reasoning power
= Intelligence
Any other method of achieving intelligence?
1111 of 45 of 45
Top-down - build logical equivalents, e.g. LOGIC, Expert systems
Bottom-up - build physical equivalents, e.g. perceptrons, neural nets
1212 of 45 of 45
The Turing test: If a person interacting with an entity from a remote location is unable to judge whether he/she is dealing with a computer or a human, and the entity a machine, it is said to possess intelligence.
?
THE TEST FOR MACHINE INTELLIGENCE
Questions
Responses
1313 of 45 of 45
THE NATURE OFKNOWLEDGE
1414 of 45 of 45
KNOWLEDGE
facts,constraints,problems, goals,procedures.
Knowledge: information organized forproblem solving
1515 of 45 of 45
Two types of knowledge: Declarative – Knowledge about an object (size, shape etc.)Procedural – Knowledge about how to do something. (how to install memory)
THE NATURE OF KNOWLEDGE
1616 of 45 of 45
KNOWLEDGE REPRESENTATIONA Sampling of Knowledge
How to install a water pump The definition of a “field goal” Painters & styles from the modern era The process of becoming a GSA contractor The architectural differences between AMD &
Intel chips The meaning of “Lousiana report” in the context
of a faculty committee meeting.
1717 of 45 of 45
KNOWLEDGE REPRESENTATION
1818 of 45 of 45
KNOWLEDGE REPRESENTATION
Logic (Predicate logic) Frames Scripts Semantic nets (Snets) Rules
Knowledge representation is concerned withhow to encode knowledge
1919 of 45 of 45
IDENTIFY THESE AS EXAMPLESOF LOGIC, FRAMES, SCRIPTS…
sister_of(X,Y), bird_of_prey(X),father_of(robin, Y)father_of(robin,_)
EXAMPLE 1
EXAMPLE 2
is_a : dbmssoftware cost : $3,000License cost : check_with_vendor no of users : 2000 Max # of tables : 10,000Supports ODBC : Yes
If # of users > 300 then, license fee = $500
If # of users < 300 then, license fee = $300
EXAMPLE 3
2020 of 45 of 45
EXAMPLES OF KNOWLEDGEREPRESENTATIONS..
P PTRANS P to P.O.P ATTEND eyes to counterP MBUILD line positionP PTRANS P to lineP PTRANS M to XX PTRANS Stamps to P
EXAMPLE 4
Eagle
Bird
Is-a
1.5 m
MaxWingspan
20 Knots
MaxSpeed
Bird-of-prey
Is-a
EXAMPLE 5
2121 of 45 of 45
Based on associative memory “node” + “link” formalism nodes represent concepts or values links can be structural or descriptive
represent structure or characteristic
NOTES ON SEMANTIC NETS
2222 of 45 of 45
Origins in S-R paradigms Thought to be used by experts Have a IF…THEN… format
Note: S-R: stimulus/response
NOTES ON RULES
2323 of 45 of 45
A description (conceptual representation) of actions in a pre-defined situation Originated from film industry Consists of actors/props Act in predictable ways
NOTES ON SCRIPTS
2424 of 45 of 45
EXAMPLE OF LOGIC
facts:has_qualification(brad,3.2,620).has_qualification(jill,4.0,540).has_qualification(ted,3.5,320).has_qualification(matt,3.8, 600).
Predicates:select(X) :- has_qualification(X,GPA,GMAT),
GPA>3.2, GMAT>550;
Goals:select(brad)? jill? ted? matt?
2525 of 45 of 45
Identify whether the following types of knowledge are declarative or procedural and identify a suitable representation scheme, give rationale:
1. Admit students to MBA program if they have a gmat score of > 5502. A description of computing facilities at WIU. 3. A proof of the theorem that any triangle circumscribed by a semi-circle will always be a right angled triangle4. Instructions for assembling a PC5. Family relationships -- X and Y are the parents of P & Q; P has a maternal aunt Z. 6. Stages in a software life cycle -- analysis, design, implementation etc.
FOR DISCUSSION
2626 of 45 of 45
The brain
Dendrites
Neurons
Neural Net(a math model)
NEURAL NETS
Mathematical models to simulate neural models of the brain,Often used in applications requiring pattern recognition e.g.crime, fraud, intrusion detection etc.
eyesnose
hair color gait
2727 of 45 of 45
BUSINESS APPLICATIONS OF AI
Automated voice response Text mining Production applications
machine design robotics paper thickness
Scheduling of cranes Credit approval
2828 of 45 of 45
INDUSTRIAL APPLICATIONS OF AI
Driverless vehicles Facial recognition Crime prevention Pothole recognition Drones
2929 of 45 of 45
Can a machine ever have the intelligence of a human being?
Has Turing’s test been passed? Why did early researchers concentrate on Chess? If we make use of a frog’s brain to process stimuli, is that
an example of a Top-Down or a Bottom-up approach? What branch of AI does the work on perceptrons
resemble? What “hardware” item is essential equipment for vision
systems? Are robots useful in industry? How? If a machine is taking dictation, is it necessary to
understand the text or can it be done mechanically?
3030 of 45 of 45
The End!
Please note there are only 29 slides