Upload
britton-riley
View
229
Download
0
Tags:
Embed Size (px)
Citation preview
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 perceptionsconceptsactions)
• 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* searchS0
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– cameraimagescorners/edges/surfaces
objectsstate 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