Transcript Artificial Intelligence

CSM6120
Introduction to Intelligent Systems
Introduction to the module
[email protected]
Commitment

20hrs seminars

6hrs practical

Rest of time spent background reading and on
assignments/presentation


4hrs seminars allocated to group presentation prep
Assessment:


Assignment 1= 40%
Assignment 2 = 60%
(presentation + report)
(coding + report)
How to succeed in this course

Manage your time wisely


Previous students have sometimes struggled with the intensive
nature of the course
Plan for the deadlines

Do lots of background reading, and read around the
subject

If you’re stuck, then ask!

Ask a fellow student or ask me
Module content
Introduction to AI
Search – uninformed and informed
Knowledge representation
Propositional and First-Order Logic
Rule-based systems
Knowledge acquisition
Neural nets and subsymbolic learning
1.
2.
3.
4.
5.
6.
7.

Course notes etc will be made available in:

http://www.aber.ac.uk/~dcswww/Dept/Teaching/CourseNotes/20122013/CSM6120/
Timing

Today: CSM6120 starts


This week: Assignment 1 handed out
Next week: Assignment 2 handed out

October 19th CSM6120 teaching ends



Presentations on Thursday 18th
Assignment 1 due in on the Friday 26th
November 2nd CSM6120 assignment 2 deadline
Timing
1
prep
2
prep
pres
Hand
in 1
Hand
in 2
Book list

Russell, S. and Norvig, P. - Artificial Intelligence : a modern
approach, 3rd edn, Prentice Hall, 2010


(previous editions just as useful, though there have been a few
amendments)
(first chapter: http://www.eecs.berkeley.edu/~russell/intro.html)

Luger, G. - Artificial intelligence : structures and
strategies for complex problem solving, Pearson
Addison-Wesley, 2009

Coppin, B. - Artificial Intelligence Illuminated, Jones and
Bartlett Publishers, 2004
etc...

What is Artificial Intelligence?

Understand intelligent entities


Build intelligent entities


Learn more about ourselves/animals
Create things that exhibit ‘intelligence’
Study constructed intelligent entities

These constructed entities are interesting and useful in their
own right!
What is Artificial Intelligence?

Scientific Goal


To determine which ideas about knowledge representation, learning, rule
systems, search, and so on, explain various sorts of real intelligence
Engineering Goal

To solve real world problems using AI techniques such as knowledge
representation, learning, rule systems, search, and so on
AI problems

Formal tasks - playing board or card games, solving
puzzles, mathematical and logic problems

Expert tasks - medical diagnosis, engineering, scheduling,
computer hardware design

Mundane tasks - everyday speech, written language,
perception, walking, handling
What is Artificial Intelligence?

“Artificial Intelligence (AI) is the part of CS concerned with designing
intelligent computer systems, that is, systems that exhibit
characteristics we associate with intelligence in human behaviour –
understanding language, learning, reasoning, solving problems, and
so on.” (Barr & Feigenbaum, 1981)

“The study of the computations that make it possible to perceive,
reason, and act” (Winston, 1992)

“The branch of computer science that is concerned with the
automation of intelligent behaviour” (Luger and Stubblefield,
1993)
History of AI

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 Dean Edmonds (1951) constructed the first neural
network computer



Made out of 3000 vacuum tubes and a surplus automatic pilot mechanism
from a B-24 bomber
Simulated a network of 40 neurons
1950: Alan Turing’s Computing Machinery and Intelligence


First complete vision of AI
Anticipated all major arguments against AI in following 50 years
History of AI

1956: Dartmouth Workshop


Brings together top minds on automata theory, neural nets and the study
of intelligence
Allen Newell and Herbert Simon: the logic theorist (first non-numerical
thinking program used for theorem proving)



Proved 38 of the first 52 theorems in Principia Mathematica, found more
elegant proofs for some
For the next 20 years the field was dominated by these participants
1952-1969



Newell and Simon introduced the General Problem Solver: imitation of
human problem-solving
Arthur Samuel investigated game playing (checkers) with great success
John McCarthy (inventor of Lisp)

Logic oriented, Advice Taker (separation between knowledge and reasoning)
History of AI

The first generation of AI researchers made these predictions
about their work:





1957, Simon and Newell: "within ten years a digital computer will be the
world's chess champion" and "within ten years a digital computer will
discover and prove an important new mathematical theorem."
1965, Simon: "machines will be capable, within twenty years, of doing any
work a man can do."
1967, Marvin Minsky: "Within a generation ... the problem of creating
'artificial intelligence' will substantially be solved."
1970, Marvin Minsky: "In from three to eight years we will have a
machine with the general intelligence of an average human being.“
Expectations were high!
History of AI

Collapse in AI research (1966 - 1973)

Progress was slower than expected


Some systems lacked scalability


Unrealistic predictions
Combinatorial explosion in search
Fundamental limitations on techniques and representations


Minsky and Papert (1969) Perceptrons
Research funding for neural net research soon dwindled to almost
nothing
History of AI

AI revival through knowledge-based systems (1969-1970)

General-purpose vs. domain specific


Expert systems


MYCIN to diagnose blood infections (Feigenbaum et al.) –
introduction of uncertainty in reasoning
Increase in knowledge representation research


E.g. the DENDRAL project (Buchanan et al. 1969) – first successful
knowledge intensive system (large numbers of rules)
Logic, frames, semantic nets, …
AI winter (1974-1980)

Lighthill report highly critical of some areas
History of AI

AI becomes an industry (1980 - present)



Connectionist revival (1986 - present)



XCON at DEC (1980) – saved the company $40m p.a.
Fifth Generation Project in Japan (1981) – $850m to build
machines that could make conversations, translate languages,
interpret pictures, and reason like humans
Parallel distributed processing (Rumelhart and McClelland,1986);
backpropagation
Symbolic models vs connectionism
AI becomes a science (1987 - present)
History of AI

1990s




Emergence of intelligent agents: bots!
Machine learning
Genetic algorithms
2000+




Dealing with large datasets
Swarm intelligence
...
Large field, lots of applications
AI and Games

Classic Games


Noughts and Crosses
Chess - Deep Blue 1997




1957 - Newell and Simon predicted that a computer would be chess
champion within ten years
Simon : “I was a little far-sighted with chess, but there was no way to
do it with machines that were as slow as the ones way back then”
Connect 4, Othello, Backgammon, Scrabble, Bridge, Go
Current Games



Strategy/Tactical/Combat (F.E.A.R., Crysis)
RPG/Adventure
Artificial Life (Creatures, Spore)
AI approaches


Thinking vs Acting
Human vs Rational
(acting = behaviour)
(rationality = doing the right thing)
Systems that
think like humans
Systems that
think rationally
(cognitive science)
(logic/laws of thought)
Systems that act
like humans
Systems that act
rationally
(c.f. Turing test)
(agents)
Artificial Intelligence

AI often burdened with over-promising and grandiosity

The gap between AI engineering and AI as a model of
intelligence is so large that trying to bridge it almost inevitably
leads to assertions that later prove embarrassing

McCarthy said AI was “the science and engineering of
making intelligent machines”

So how can we determine if a program is intelligent?
Strong vs Weak AI

Debate as to whether some forms of AI can truly
reason and solve problems



Strong AI: Machine can actually think intelligently
Weak AI: Machine can possibly act intelligently
John Searle

“...according to strong AI, the computer is not merely a tool in the
study of the mind; rather, the appropriately programmed computer
really is a mind”
Turing Test (1950)
Human
interrogator
Human
?
AI System

Turing's argument is essentially: “If a computer can fool a
judge into thinking it is human, we must acknowledge it is
able to think like a human”
Turing Test (1950)

What techniques are required?




Natural language processing to enable it to communicate
successfully in English (or some other human language)
Knowledge representation to store information provided
before or during the interrogation
Automated reasoning to use the stored information to
answer questions and to draw new conclusions
Machine learning to adapt to new circumstances and to
detect and extrapolate patterns
Turing Test (1950)

AI researchers have devoted little effort to passing the
Turing test


Believe that studying principles of intelligence is more
important than duplicating something else
Precedent? The quest for artificial flight


Succeeded when people stopped imitating birds and learned
aerodynamics
Aeronautical engineering does not define its goal as making
“machines that fly so exactly like pigeons that they can fool
even other pigeons”
Chinese Room

Searle argued that behaving intelligently was not enough
(1980)

Thought experiment - the Chinese Room





You are in a room with an opening through which Chinese
sentences are passed
You have a rule book that allows you to look up these
sentences although you do not speak Chinese
The book tells you how to reply to them in Chinese
You can then behave in an apparently intelligent way
(video)
Chinese Room

Searle claimed that although they appeared intelligent,
computers would be using the equivalent of a rule book

The rule book and stacks of paper, just being paper, do not
understand Chinese

Within the article setting out the Chinese Room experiment,
Searle set out some possible arguments against his contention
that the individual in the Chinese Room could not be said to
understand

What does it all mean?
The Chinese Room argument has provoked much discussion
Watson

In 2011, Watson beat the two most successful Jeopardy
players


http://www.bbc.co.uk/news/technology-12491688
http://www.bbc.co.uk/news/technology-17547694

But is this intelligence???

DeepQA article:


http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=617
7810
http://www.aaai.org/Magazine/Watson/watson.php
Ethics and AI

We’ve looked at whether we can develop AI, but not
whether we should

The problems that AI poses:





People might lose jobs to automation
People might have too much/little leisure time
People might lose some of their privacy rights
Loss of accountability – who’s to blame if things go wrong?
Success of AI might mean end of human race!

Almost any technology has the potential to cause harm in the wrong
hands
Branches of AI (John McCarthy)

Logical AI: What a program knows about the world in general the facts of the specific

Search: AI programs often examine large numbers of possibilities, e.g. moves in a chess

Pattern recognition: When a program makes observations of some kind, it is

Representation: Facts about the world have to be represented in some way.
situation in which it must act, and its goals are all represented by sentences of some
mathematical logical language. The program decides what to do by inferring that certain
actions are appropriate for achieving its goals.
game or inferences by a theorem proving program. Discoveries are continually made about
how to do this more efficiently in various domains.
often programmed to compare what it sees with a pattern. For example, a vision program
may try to match a pattern of eyes and a nose in a scene in order to find a face. More
complex patterns, e.g. in a natural language text, in a chess position, or in the history of some
event are also studied. These more complex patterns require quite different methods than do
the simple patterns that have been studied the most.
Usually languages of mathematical logic are used.
Branches of AI (John McCarthy)

Inference: From some facts, others can be inferred. Mathematical logical deduction is

Commonsense knowledge and reasoning: This is the area in

Learning from experience: Programs do that. The approaches to AI based
adequate for some purposes, but new methods of non-monotonic inference have been added
to logic since the 1970s. The simplest kind of non-monotonic reasoning is default reasoning in
which a conclusion is to be inferred by default, but the conclusion can be withdrawn if there is
evidence to the contrary. Ordinary logical reasoning is monotonic in that the set of
conclusions that can the drawn from a set of premises is a monotonic increasing function of
the premises.
which AI is farthest from human-level, in spite of the fact that it has been an active research
area since the 1950s. While there has been considerable progress, e.g. in developing systems of
non-monotonic reasoning and theories of action, yet more new ideas are needed.
on connectionism and neural nets specialize in that. There is also learning of laws expressed in
logic. Programs can only learn what facts or behaviours their formalisms can represent, and
unfortunately learning systems are almost all based on very limited abilities to represent
information.
Branches of AI (John McCarthy)

Planning: Planning programs start with general facts about the world (especially facts

Epistemology: This is a study of the kinds of knowledge that are required for solving

Ontology: Ontology is the study of the kinds of things that exist. In AI, the programs

Heuristics: A heuristic is a way of trying to discover something or an idea embedded in

Genetic programming: Genetic programming is a technique for getting
about the effects of actions), facts about the particular situation and a statement of a goal.
From these, they generate a strategy for achieving the goal. In the most common cases, the
strategy is just a sequence of actions.
problems in the world.
and sentences deal with various kinds of objects, and we study what these kinds are and what
their basic properties are. Emphasis on ontology began in the 1990s.
a program. The term is used variously in AI. Heuristic functions are used in some approaches
to search to measure how far a node in a search tree seems to be from a goal. Heuristic
predicates that compare two nodes in a search tree to see if one is better than the other, i.e.
constitutes an advance toward the goal, may be more useful.
programs to solve a task by mating random programs and selecting fittest in millions of
generations.