Artificial Intelligence
What is AI?
• Can machines “think”?
• Can machines be truly autonomous?
• Can machines program themselves?
• Can machines learn?
• Will they ever be “conscious”, and is that
necessary?
• media depictions of AI (science fiction)
– HAL in 2001: Space Odessey
– Spielberg’s AI
– Data on Star Trek Next Generation
– ...
• real AI has many practical applications
– credit evaluation, medical diagnosis
– guidance systems, surveillance
– manufacturing (robotics, logistics)
– information kiosks, computer-aided tutoring
– AI in video games (also: Deep Blue, chess)
– driverless vehicles, UAVs
– Mars rover, Hubble telescope
• AI has a long history, and draws on many
fields
– mathematics, computability, formal logic
– control theory
– optimization
– cognitive science
– linguistics
Perspectives on AI
• Philosophical
– What is the nature of intelligence?
• Psychological
– How do humans think?
• Engineering
– advanced methods for building complex
systems that solve hard real-world problems
Philosophical Perspective
• started with Greek philosophers (e.g. Aristotle)
– syllogisms
– natural categories
• 1700-1800s: development of logic, calculus
– Descartes, Liebnitz, Boole, Frege, Tarski, Russell
– what are concepts? existence, intention, causality...
– reductionist approaches to try to mechanize reasoning
• 1900s: development of computers
– input/output model
– is intelligence a “computable function”?
– Turing, von Neumann, Gödel
• Does “intelligence” require a physical brain?
– Programmed devices will probably never have
“free will”
• Or is it sufficient to produce intelligent
behavior, regardless of how it works?
• The Turing Test
– first published in 1950
– a panel of human judges asks questions through
a teletype interface (restricted to topic areas)
– a program is intelligent if it can fool the judges
and look indistinguishable from other humans
– annual competition at MIT: the Loebner Prize
• chatterbots
Psychological Perspective
• AI is about understanding and modeling
human intelligence
• Cognitive Science movement (ca. 1950s)
– replace stimulus/response model
– internal representations
– mind viewed as “information processor”
(sensory perceptionsconceptsactions)
• Are humans a good model of intelligence?
– strengths:
• interpretation, dealing with ambiguity, nuance
• judgement (even for ill-defined situations)
• insight, creativity
• adaptiveness
– weaknesses:
• slow
• error-prone
• limited memory
• subject to biases
• influenced by emotions
Optimization
• AI draws upon (and extends) optimization
– remember NP-hard problems?
• there is (probably) no efficient algorithm that solves them in
polynomial time
– but we can have approximation algorithms
• run in polynomial time, but don’t guarantee optimal solution
– classic techniques: linear programming, gradient descent
• Many problems in AI are NP-hard (or worse)
• AI gives us techniques for solving them
– heuristic search
– use of expertise encoded in knowledge bases
– AI relies heavily on greedy algorithms, e.g. for scheduling
– custom algorithms for search (e.g. constraint
satisfaction), planning (e.g. POP, GraphPlan), learning
(e.g. rule generation), decision making (MDPs)
Planning
• Autonomy – we want computers to figure out
how to achieve goals on their own
– Given a goal G
– and a library of possible actions Ak
– find a sequence of actions A1..An
– that changes the state of the worlds to achieve G
current state of world desired state of world
pickup(A)
puton(A,table)
pickup(C)
puton(C,A)
pickup(B)
pickup(B,C)
• Examples:
– Blocks World – stack blocks in a desired way
– traveling from College Station to Statue of Liberty
– rescuing a victim in a collapsed building
– cooking a meal
• The challenges of planning are:
– for each task, must invoke sub-tasks to ensure pre-
conditions are satisfied
• in order to nail 2 pieces of wood together, I have to have a
hammer
– sub-tasks might interact with each other
• if I am holding a hammer and nail, I can’t hold the boards
– so planning is a combinatorial problem
Intelligent Agents
• agents are: 1) autonomous, 2) situated in an
environment they can change, 3) goal-oriented
• agents focus on decision making
• incorporate sensing, reasoning, planning
– sense-decide-act loop
• rational agents try to maximize a utility
function (rewards, costs)
goals KB initial state
goal state
perception
action
agent environment
• agents often interact in multi-agent systems
– collaborative
• teamwork, task distribution
• information sharing/integration
• contract networks
• voting
• remember Dr. Shell’s multi-robots
– competitive
• agents will maximize self utility in open systems
• negotiation
• auctions, bidding
• game theory
• design mechanisms where there is incentive to
cooperate
Core Concepts in AI
• Symbolic Systems Hypothesis
– intelligence can be modeled as manipulating symbols
representing discrete concepts
• like Boolean variables for CupEmpty, Raining, LightsOn,
PowerLow, CheckmateInOneMove, PedestrianInPath...
• inference and decision-making comes from comparing
symbols and producing new symbols
– Herbert Simon, Allan Newell (CMU, 1970s)
• (A competing idea: Connectionism)
– neural networks
– maybe knowledge can’t be represented by discrete
concepts, but is derived from associations and their
strengths
– good model for perception and learning
Core Concepts in AI
• Search
– everything in AI boils down to discrete search
– search space: different possible actions
branch out from initial state
– finding a goal
• weak methods: depth-first search (DFS), breadth-
first search (BFS), constraint satisfaction (CSP)
• strong methods: use ‘heuristics’, A* search
S0
goal nodes
• Applications of search
– game search (tic-tac-toe, chess)
– planning
– natural language parsing
– learning (search for logical rules that describe
all the positive examples and no negative
examples by adding/subtracting antecedents)
• Knowledge-representation
– attempt to capture expertise of human experts
– build knowledge-based systems, more powerful
than just algorithms and code
– “In the knowledge lies the power” (Ed
Feigenbaum, Turing Award: 1994 )
– first-order logic
• p vegetarian(p)↔(f eats(p,f)m meat(m)contains(f,m))
• x,y eat(joe,x)contains(x,y)fruit(y)vegetable(y)
•  vegetarian(joe)
– inference algorithms
• satisfiability, entailment, modus ponens, backward-
chaining, unification, resolution
Core Concepts in AI
• Expert Systems
– Medical diagnosis: rules for linking symptoms
with diseases, from interviews with doctors
– Financial analysis: rules for evaluating credit
score, solvency of company, equity-to-debt
ratio, sales trends, barriers to entry
– Tutoring – rules for interpreting what a student
did wrong on a problem and why, taxonomy of
possible mis-conceptions
– Science – rules for interpreting chemical
structures from mass-spectrometry data, rules
for interpreting well logs and finding oil
• Major problem with many expert systems:
brittleness
• Major issue in AI today: Uncertainty
– using fuzzy logic for concepts like “good
management team”
– statistics: conditional probability that a patient
has meningitis given they have a stiff neck
– Markov Decision Problems: making decisions
based on probabilities and payoffs of possible
outcomes
Sub-areas within AI
• Natural language
– parsing sentences, representing meaning, metaphor,
answering questions, translation, dialog systems
• Vision
– cameraimagescorners/edges/surfaces
objectsstate description
– occlusion, shading, textures, face recognition,
stereo(3D), motion(video)
• Robotics – configuration/motion planning
• Machine Learning (machines can adapt!)
– decision trees, neural networks, linear classifiers
– extract characteristic features from a set of examples

ArtificialIntelligence.ppt

  • 1.
  • 2.
    What is AI? •Can machines “think”? • Can machines be truly autonomous? • Can machines program themselves? • Can machines learn? • Will they ever be “conscious”, and is that necessary?
  • 3.
    • media depictionsof AI (science fiction) – HAL in 2001: Space Odessey – Spielberg’s AI – Data on Star Trek Next Generation – ... • real AI has many practical applications – credit evaluation, medical diagnosis – guidance systems, surveillance – manufacturing (robotics, logistics) – information kiosks, computer-aided tutoring – AI in video games (also: Deep Blue, chess) – driverless vehicles, UAVs – Mars rover, Hubble telescope
  • 4.
    • AI hasa long history, and draws on many fields – mathematics, computability, formal logic – control theory – optimization – cognitive science – linguistics
  • 5.
    Perspectives on AI •Philosophical – What is the nature of intelligence? • Psychological – How do humans think? • Engineering – advanced methods for building complex systems that solve hard real-world problems
  • 6.
    Philosophical Perspective • startedwith Greek philosophers (e.g. Aristotle) – syllogisms – natural categories • 1700-1800s: development of logic, calculus – Descartes, Liebnitz, Boole, Frege, Tarski, Russell – what are concepts? existence, intention, causality... – reductionist approaches to try to mechanize reasoning • 1900s: development of computers – input/output model – is intelligence a “computable function”? – Turing, von Neumann, Gödel
  • 7.
    • Does “intelligence”require a physical brain? – Programmed devices will probably never have “free will” • Or is it sufficient to produce intelligent behavior, regardless of how it works? • The Turing Test – first published in 1950 – a panel of human judges asks questions through a teletype interface (restricted to topic areas) – a program is intelligent if it can fool the judges and look indistinguishable from other humans – annual competition at MIT: the Loebner Prize • chatterbots
  • 8.
    Psychological Perspective • AIis about understanding and modeling human intelligence • Cognitive Science movement (ca. 1950s) – replace stimulus/response model – internal representations – mind viewed as “information processor” (sensory perceptionsconceptsactions)
  • 9.
    • Are humansa good model of intelligence? – strengths: • interpretation, dealing with ambiguity, nuance • judgement (even for ill-defined situations) • insight, creativity • adaptiveness – weaknesses: • slow • error-prone • limited memory • subject to biases • influenced by emotions
  • 10.
    Optimization • AI drawsupon (and extends) optimization – remember NP-hard problems? • there is (probably) no efficient algorithm that solves them in polynomial time – but we can have approximation algorithms • run in polynomial time, but don’t guarantee optimal solution – classic techniques: linear programming, gradient descent • Many problems in AI are NP-hard (or worse) • AI gives us techniques for solving them – heuristic search – use of expertise encoded in knowledge bases – AI relies heavily on greedy algorithms, e.g. for scheduling – custom algorithms for search (e.g. constraint satisfaction), planning (e.g. POP, GraphPlan), learning (e.g. rule generation), decision making (MDPs)
  • 11.
    Planning • Autonomy –we want computers to figure out how to achieve goals on their own – Given a goal G – and a library of possible actions Ak – find a sequence of actions A1..An – that changes the state of the worlds to achieve G current state of world desired state of world pickup(A) puton(A,table) pickup(C) puton(C,A) pickup(B) pickup(B,C)
  • 12.
    • Examples: – BlocksWorld – stack blocks in a desired way – traveling from College Station to Statue of Liberty – rescuing a victim in a collapsed building – cooking a meal • The challenges of planning are: – for each task, must invoke sub-tasks to ensure pre- conditions are satisfied • in order to nail 2 pieces of wood together, I have to have a hammer – sub-tasks might interact with each other • if I am holding a hammer and nail, I can’t hold the boards – so planning is a combinatorial problem
  • 13.
    Intelligent Agents • agentsare: 1) autonomous, 2) situated in an environment they can change, 3) goal-oriented • agents focus on decision making • incorporate sensing, reasoning, planning – sense-decide-act loop • rational agents try to maximize a utility function (rewards, costs) goals KB initial state goal state perception action agent environment
  • 14.
    • agents ofteninteract in multi-agent systems – collaborative • teamwork, task distribution • information sharing/integration • contract networks • voting • remember Dr. Shell’s multi-robots – competitive • agents will maximize self utility in open systems • negotiation • auctions, bidding • game theory • design mechanisms where there is incentive to cooperate
  • 15.
    Core Concepts inAI • Symbolic Systems Hypothesis – intelligence can be modeled as manipulating symbols representing discrete concepts • like Boolean variables for CupEmpty, Raining, LightsOn, PowerLow, CheckmateInOneMove, PedestrianInPath... • inference and decision-making comes from comparing symbols and producing new symbols – Herbert Simon, Allan Newell (CMU, 1970s) • (A competing idea: Connectionism) – neural networks – maybe knowledge can’t be represented by discrete concepts, but is derived from associations and their strengths – good model for perception and learning
  • 16.
    Core Concepts inAI • Search – everything in AI boils down to discrete search – search space: different possible actions branch out from initial state – finding a goal • weak methods: depth-first search (DFS), breadth- first search (BFS), constraint satisfaction (CSP) • strong methods: use ‘heuristics’, A* search S0 goal nodes
  • 17.
    • Applications ofsearch – game search (tic-tac-toe, chess) – planning – natural language parsing – learning (search for logical rules that describe all the positive examples and no negative examples by adding/subtracting antecedents)
  • 18.
    • Knowledge-representation – attemptto capture expertise of human experts – build knowledge-based systems, more powerful than just algorithms and code – “In the knowledge lies the power” (Ed Feigenbaum, Turing Award: 1994 ) – first-order logic • p vegetarian(p)↔(f eats(p,f)m meat(m)contains(f,m)) • x,y eat(joe,x)contains(x,y)fruit(y)vegetable(y) •  vegetarian(joe) – inference algorithms • satisfiability, entailment, modus ponens, backward- chaining, unification, resolution Core Concepts in AI
  • 19.
    • Expert Systems –Medical diagnosis: rules for linking symptoms with diseases, from interviews with doctors – Financial analysis: rules for evaluating credit score, solvency of company, equity-to-debt ratio, sales trends, barriers to entry – Tutoring – rules for interpreting what a student did wrong on a problem and why, taxonomy of possible mis-conceptions – Science – rules for interpreting chemical structures from mass-spectrometry data, rules for interpreting well logs and finding oil
  • 20.
    • Major problemwith many expert systems: brittleness • Major issue in AI today: Uncertainty – using fuzzy logic for concepts like “good management team” – statistics: conditional probability that a patient has meningitis given they have a stiff neck – Markov Decision Problems: making decisions based on probabilities and payoffs of possible outcomes
  • 21.
    Sub-areas within AI •Natural language – parsing sentences, representing meaning, metaphor, answering questions, translation, dialog systems • Vision – cameraimagescorners/edges/surfaces objectsstate description – occlusion, shading, textures, face recognition, stereo(3D), motion(video) • Robotics – configuration/motion planning • Machine Learning (machines can adapt!) – decision trees, neural networks, linear classifiers – extract characteristic features from a set of examples