Artificial Intelligence

1
Artificial Intelligence
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 depictions of AI (science fiction)
• HAL in 2001 Space Odessey
• Spielbergs AI
• Data on Star Trek Next Generation
• Terminator, Skynet...
• 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 has a 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

• 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

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?
• operational definition

8

• The Turing Test
• first proposed in 1950 by Alan Turing
• 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 humans
• chatterbots
• the Loebner Prize annual competition at MIT

9
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)

10

• Are humans a good model of intelligence?
• strengths

11

• Are humans a good model of intelligence?
• strengths
• interpretation, dealing with ambiguity, nuance
• judgement (even for ill-defined situations)
• insight, creativity
• adaptiveness

12

• Are humans a good model of intelligence?
• strengths
• interpretation, dealing with ambiguity, nuance
• judgement (even for ill-defined situations)
• insight, creativity
• adaptiveness
• weaknesses

13

• 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

14
Optimization

• AI draws upon optimization methods
• 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 dont 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)

15
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
16
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

pickup(A)
puton(A,table)
pickup(C)
puton(C,A)
pickup(B)
current state of world
desired state of world
pickup(B,C)
17

• 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 cant hold
  the boards
• so planning is a combinatorial problem

18
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)

19

• agents often interact in multi-agent systems
• collaborative
• teamwork, task distribution
• information sharing/integration
• contract networks
• voting
• competitive
• agents will maximize self utility in open systems
• negotiation
• auctions, bidding
• game theory
• design mechanisms where there is incentive to
  cooperate

20
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 cant be represented by discrete
  concepts, but is derived from associations and
  their strengths
• good model for perception, motor skills, and
  learning

21
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

goal nodes
22

• 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)

23
Core Concepts in AI

• 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

24

• 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

25

• 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

26
Traditional Sub-areas within AI

• Natural language processing
• parsing sentences, representing meaning,
  metaphor, answering questions, translation,
  dialog systems
• Vision
• camera?images?corners/edges/surfaces ?objects?stat
  e description
• occlusion, shading, textures, face recognition,
  stereo(3D), motion(video)
• Robotics configuration/motion planning

27

• Machine Learning
• machines can adapt!
• learn from experience
• extract patterns from examples
• algorithms for decision trees, neural networks,
  linear classifiers...