Today’s Lecture Goal: what’s AI about anyway? A brief history The state of the art Three key...
-
Upload
letitia-cooper -
Category
Documents
-
view
214 -
download
0
Transcript of Today’s Lecture Goal: what’s AI about anyway? A brief history The state of the art Three key...
Today’s Lecture
• Goal: what’s AI about anyway?
• A brief history
• The state of the art
• Three key ideas: – Search, Representation/Modeling,
Learning
AI Hypothesis
The Brain is a Computer
What are the computational principles?
How can we find them out?
How will we know if we succeed?
Analogy: Birds fly but we don’t build planes with feathers and flapping wings.
Artificial Intelligence– Methods for applying computers to problems
that require “intelligence”– Study of the fundamental limits of
“intelligent” behavior by computers
What is AI?• There is no universal definition. Here
are some common ones:– Systems that think like humans
• “machines with minds”
– Systems that act like humans• “machine that perform functions that require
intelligence when performed by people”• “to make computers do things at which, at the
moment, people are better”
– Systems that think rationally• “the study of mental faculties through the use
of computational models”
– Systems that act rationally• “intelligent behavior in artifacts”
Acting Humanly: The Turing Test
• The Turing Test was designed to test whether an AI system act humanly.
• A human interrogator (judge) interacts with two subjects: a human and an AI system. The AI system passes the test if the judge cannot tell which one is the human.
What is AI?
• Artificial intelligence ("AI") can mean many things to many people.Much confusion arises because the word 'intelligence' is ill-defined.The phrase is so broad that people have found it useful to divide AI into two classes:
strong AI and
weak AI.
What's the difference between strong AI and weak AI?
• Strong AI makes the bold claim that computers can be made to think on a level (at least) equal to humans and possibly even be conscious of themselves.
• Weak AI simply states that some "thinking-like" features can be added to computers to make them more useful tools... and this has already started to happen (witness expert systems, drive-by-wire cars and speech recognition software).
19 april 2023 10AI 1
A brief history
• What happened after WWII?– 1943: Warren Mc Culloch and Walter Pitts: a model of artificial
boolean neurons to perform computations.• First steps toward connectionist computation and learning (Hebbian
learning).
• Marvin Minsky and Dann Edmonds (1951) constructed the first neural network computer
– 1950: Alan Turing’s “Computing Machinery and Intelligence”• First complete vision of AI.
19 april 2023 11AI 1
A brief history (2)
• The birth of AI (1956)– Darmouth Workshop bringing together top minds on automata theory,
neural nets and the study of intelligence.• Allen Newell and Herbert Simon: The logic theorist (first nonnumerical thinking
program used for theorem proving)• For the next 20 years the field was dominated by these participants.
– Great expectations (1952-1969)• Newell and Simon introduced the General Problem Solver.
– Imitation of human problem-solving
• Arthur Samuel (1952-)investigated game playing (checkers ) with great success.• John McCarthy(1958-) :
– Inventor of Lisp (second-oldest high-level language)– Logic oriented, Advice Taker (separation between knowledge and reasoning)
19 april 2023 12AI 1
A brief history (3)
• The birth of AI (1956)– Great expectations continued ..
• Marvin Minsky (1958 -)– Introduction of microworlds that appear to require intelligence to solve: e.g. blocks-
world.– Anti-logic orientation, society of the mind.
• Collapse in AI research (1966 - 1973)– Progress was slower than expected.
• Unrealistic predictions.
– Some systems lacked scalability.• Combinatorial explosion in search.
– Fundamental limitations on techniques and representations.• Minsky and Papert (1969) Perceptrons.
19 april 2023 13AI 1
A brief history (4)
• AI revival through knowledge-based systems (1969-1970)– General-purpose vs. domain specific
• E.g. the DENDRAL project (Buchanan et al. 1969)– First successful knowledge intensive system.
– Expert systems • MYCIN to diagnose blood infections (Feigenbaum et al.)
– Introduction of uncertainty in reasoning.
– Increase in knowledge representation research.• Logic, frames, semantic nets, …
19 april 2023 14AI 1
A brief history (5)
• AI becomes an industry (1980 - present)– R1 at DEC (McDermott, 1982)– Fifth generation project in Japan (1981)– American response …
• Puts an end to the AI winter.
• Connectionist revival (1986 - present)– Parallel distributed processing (RumelHart and McClelland, 1986);
backprop.
19 april 2023 15AI 1
A brief history (6)
• AI becomes a science (1987 - present)– Neats vs. scruffies.
• In speech recognition: hidden markov models• In neural networks• In uncertain reasoning and expert systems: Bayesian network formalism• …
• The emergence of intelligent agents (1995 - present)– The whole agent problem:
“How does an agent act/behave embedded in real environments with continuous sensory inputs”
Which of the following can be done by computers/robots at present?
• Play a decent game of table tennis
• Drive a car in Causeway Bay
• Buy a week’s worth of food at a supermarket
• Buy a week’s worth of food on the Web
• Discover and prove new mathematical theorems
Which of the following can be done by computers/robots at present?
• Give competent legal advice in a specialized area of law
• Translate spoken English into spoken Swedish in real time
• Perform a complex surgical operation
• Play a soccer match with other “robot” teammates
• Chat with a human
• Vacuum-clean the floor of a house
Open vs Closed Tasks
• Natural language understanding
• Teaching chess• Image understanding• Learning to program
• Robot to wash dishes
• Achieveable?
• Playing chess• Identifying zip codes• Learning to diagnosis known
diseases
• Robot to distribute mail (mobots)
• All achievable
Areas of Study in AI
• Reasoning (inference), optimization, resource allocation– planning, scheduling, real-time problem solving,
intelligent assistants, internet agents• Natural Language Processing
– information retrieval, summarization, understanding, generation, translation
• Vision– image analysis, recognition, scene understanding
• Robotics– grasping/manipulation, locomotion, motion planning,
mapping
Surprises in AI research
• Tasks difficult for humans have turned out to be “easy”– Chess– Checkers, Othello, Backgammon– Logistics planning– Airline scheduling– Fraud detection– Sorting mail– Proving theorems– Crossword puzzles
Surprises in AI research
• Tasks easy for humans have turned out to be hard.– Speech recognition– Face recognition– Composing music/art– Autonomous navigation– Motor activities (walking)– Language understanding– Common sense reasoning (example: how many
legs does a fish have?)
Do you agree?
• “As computers do only what their programmers tell them to do, they cannot be intelligent.”
• “As animals do only what their genes tell them to do, they cannot be intelligent.”
• “As animals, humans, and computers do only what their atoms/molecules tell them to do, they cannot be intelligent.”
Do you agree?
• “As computers do only what their programmers tell them to do, they cannot be emotional.”
• “As animals do only what their genes tell them to do, they cannot be emotional.”
• “As animals, humans, and computers do only what their atoms/molecules tell them to do, they cannot be emotional.”
Why do AI?
• Two main goals of AI:– To understand human intelligence better.
We test theories of human intelligence by writing programs which emulate it.
– To create useful “smart” programs able to do tasks that would normally require a human expert.
Who does AI?
• Many disciplines contribute to goal of creating/modelling intelligent entities:– Computer Science– Psychology (human reasoning)– Philosophy (nature of belief, rationality, etc)– Linguistics (structure and meaning of language)– Human Biology (how brain works)
AI is the reproduction of human reasoning and intelligent behavior by computational methods
Intelligent behavior
Humans
Computer
What is AI?an attempt of
Act like humans Act rationally
Think like humans Think rationally
What is AI?(R&N)
Discipline that systematizes and automates reasoning processes to create machines that:
The goal of AI is to create computer systems that perform tasks regarded as requiring intelligence when done by humans
AI Methodology: Take a task at which people are better, e.g.:• Prove a theorem• Play chess• Plan a surgical operation• Diagnose a disease• Navigate in a building
and build a computer system that does it automatically
But do we want to duplicate human imperfections?
Act like humans Act rationally
Think like humans Think rationally
Main Areas of AI
Knowledge representation (including formal logic)
Search, especially heuristic search (puzzles, games)
Planning Reasoning under
uncertainty, including probabilistic reasoning
Learning Agent architectures Robotics and perception Natural language
processing
Search
Knowledgerep.Planning
Reasoning
Learning
Agent
RoboticsPerception
Naturallanguage
... ExpertSystems
Constraintsatisfaction
What are the branches of AI?There are many, some are 'problems' and some are 'techniques‘• Automatic Programming - The task of describing what a program should do and having the
AI system 'write' the program• Bayesian Networks - A technique of structuring and inferencing with probabilistic
information. (Part of the "machine learning"problem).
• Constraint Satisfaction - solving NP-complete problems, using variety of techniques.• Knowledge Engineering/Representation - turning what we know about a particular domain
into a form in which a computer can understand it.• Machine Learning - Programs that learn from experience or data.• Natural Language Processing (NLP) - Processing and (perhaps) understanding human
("natural") language. Also known as computational linguistics.• Neural Networks (NN) - The study of programs that function in a manner similar to how
animal brains do.• Planning - given a set of actions, a goal state, and a present state, decide which actions must
be taken so that the present state is turned into the goal state• Robotics - The intersection of AI and robotics, this field tries to get (usually mobile) robots to
act intelligently.• Speech Recognition - Conversion of speech into text.• Search - The finding of a path from a start state to a goal state. Similar to planning, yet
different...• Visual Pattern Recognition - The ability to reproduce the human sense of sight on a machine.
AI and CIArtificial Intelligence and Computational IntelligenceAI: symbolic processing and symbolic reasoning,CI: linguistic, numerical, granular reasoning.
NN (Neural Networks)FL (Fuzzy Logic)GA (Genetic Algorithms)EC (Evolutionary Computing)RS (Rough Sets)PR (Probabilistic Reasoning)GrC (Granular Computing)
Major Techniques of CI
Relations between AI and CI
Artificial intelligence (AI) is part of CI that:
•Is based on symbolic representation of knowledge
•Create expert systems that help to reason
•Knowledge engineering is its most important branch.
•AI is focused on higher cognitive processes, such as language, logic, reasoning, thinking, problem solving, sequential action.
•CI also include basic sensory signal processing, low-level cognition, perception and control, senso-motoric behaviour.
•CI methods may help to discover data hidden.
•Only a few hybrid CI-AI exit, cognitive robotics need them.
• Application of soft computing to handwriting recognition • Application of soft computing to automotive systems and manufacturing • Application of soft computing to image processing and data compression • Application of soft computing to architecture • Application of soft computing to decision-support systems • Application of soft computing to power systems • Neurofuzzy systems • Fuzzy logic control
Applications of CI