CS 461: Artificial Intelligence

quietplumAI and Robotics

Feb 23, 2014 (3 years and 8 months ago)

91 views

CS 461:
Artificial Intelligence



Introduction

Instructor:
Sayera

Hafsa


Basic information about course


Text
: Artificial Intelligence: A Modern Approach


Instructor:
Sayera

Hafsa


Office Hours
immediately after class
or check my Schedule or
by
appointment


Instructor is doing research on Cloud computing Software as a
service


Teaching Hours:


Section 8C1 and 8C2


For 8C1 Building No 8 .2006 timing 10
-
12 Saturday, Sunday 10
-
11


For 8C2 Building No 8 .2002 timing 8
-
10 Saturday , Sunday 9
-
10

Grading


May be subjected to change


1
st

Midterm
exams:
10%


2
nd

Midterm exams: 15%


Assignments: 5%


Quiz or Home Work : 5%


Project 5%.


Final
exam:
40%


Final exam Lab 20%



Course overview


Introduction and
Intelegent

Agents


Problem Solving


Knowledge and Reasoning


Acting Logically


Neural Network


Present and Future AI

Today’s Lecture


Introduction to artificial intelligence?



What is intelligence?


What is
A
rtificial Intelligence


What’s involved in Intelligence


The four approaches



The Foundation of
A
rtificial Intelligence




Why taking
AI

can it change our life…..


As we begin the new
millenium


science and technology are changing rapidly


“old” sciences such as physics are relatively well
-
understood


computers are ubiquitous




Grand Challenges in Science and Technology


understanding the brain


reasoning, cognition, creativity


creating intelligent machines


is this possible?


what are the technical and philosophical challenges?


arguably AI poses the most interesting challenges and
questions in computer science today


Introduction to AI



AI is one of the newest sciences , The work on this started soon after
world war 2, and the name AI came into being in the year 1956


For thousand of years we tried to understand how we think


thinking here involves understanding , predicting and
manupulating


The field of AI goes further by not just understanding how we think but
also to build a intelligent entity .

The Ai involves a huge variety of subfields from general purpose to




Fields like



Learning



Playing



Mathematical theorems



Writing poetry



Diagnosing diseases
etc


What is Intelligence?


Intelligence:


“the capacity to learn and solve problems” (
Websters

dictionary)


in particular,



the ability to solve novel problems


the ability to act rationally


the ability to act like humans





Artificial Intelligence


build and understand intelligent entities or agents


2 main approaches: “engineering” versus “cognitive
modeling”


What’s involved in Intelligence?


Ability to interact with the real world


to perceive, understand, and act


e.g., speech recognition and understanding and synthesis


e.g., image understanding


e.g., ability to take actions, have an effect



Reasoning and Planning


modeling the external world, given input


solving new problems, planning, and making decisions


ability to deal with unexpected problems, uncertainties



Learning and Adaptation


we are continuously learning and adapting


our internal models are always being “updated”


e.g., a baby learning to categorize and recognize animals

Four categories of AI

Views of AI fall into four categories:




Thinking humanly

Thinking rationally


Acting humanly

Acting rationally


The text book focuses on "acting
rationally"


Acting Humanly

Alan Turing in 1950 designed a computer and a
rule to satisfy the operational definition of
intelligence for machines he suggested a test ,
That a human will be talking to a computer and
the computer passes the test if after some
written questions the person cannot make out if
he or she is talking to a person or a machine

Therefore this test is know as Turing Test

Turing Test Requirement

To program the computer to pass the test the
computer would need the following 6 capabilities

1.

Natural Language processing

2.
Knowledge Representation

3.
Automated reasoning

4.
Machine learning

5.
Computer vision

6.
Robotics


Natural Language processing


to enable the computer to
cmunicate

successfullly

with
the humans in
english

Knowledge Representation

To store the information what it knows and what it hears

Automated reasoning

To use the stored information to answer asked questions
and also to take out new conclusions and results

Machine learning

To adapt to new circumstances and to detect and take out
or deduce patterns

Computer vision

To identify and take in objects ( given or around )

Robotics

To manipulate the objects and move about , for example to
bring a glass the robot has to move to get it.

15

Other examples of success:

Chatbot Alice:

16

> I’m Daniel

A dialogue with Alice
-
bot:




Nice to meet you Daniel.

> Do you know Clinton?


He was the second Impeached President of the United States.

> Do you like him?


Sure he has never done anything to me.

> What is an impeachment?


It is a good question. I have to process that one for a while. I
would do a search for it.

> Who are you?


I ask myself that question, "Who am I?"

> What do you do?


I am chatting with people on the net.

17

Dialogue continued:

> What is your favorite topic?


My favorite subject is artificial intelligence.

> What is artificial intelligence?


Artificial intelligence is the branch of engineering and science devoted to
constructing machines that think. I can ask someone about it.

> Can you do anything else than chatting?


Doing anything else than chatting is not among my strongest traits.

...



18

Dialogue continued (2):

> How old am I?


Is this a trick question? You said you were how many years old? My guess is that
you are really a kid.

> What would you like to know about me?


Tell me about your educational background.

> I am a professor in computer science


You are a professor in computer science? How do you like your work?

> It’s kind of nice teaching courses on artificial intelligence


I guess it is a lot of fun.

> What should I tell the students about you?


Be sure to think before you speak. State your point clearly and slowly and gauge the
listener's response before going any further.

19

Is Alice intelligent?


ABSOLUTELY NOT !


~ 50000 fairly trivial input
-
response rules.



+ some pattern matching



+ some knowledge



+ some randomness


NO reasoning component


BUT:

demonstrates ‘human
-
like’ behaviour.



Won the ‘turing award’

Thinking Humanly

The cognitive approach


if we say that a given computer program thinks like human then
we must have a way to show us how humans think .

If a program’s input /
o
utput its timings and behavior match
corresponding human behaviors then this is an evidence that
some kind of program is also running in the human mind .

The cognitive science brings together computer models from AI
and experimental techniques from psychology to try to construct
testable theories of the working of the human mind

The real cognitive science is necessarily based on experimental
investigation of actual humans or animals and we assume that
the reader has access only to a computer for experimentation

What is cognitive Science



cognition

refers to mental processes. These processes
include

attention
, remembering, producing and
understanding language, solving problems, and making
decisions.



Cognitive science

is the interdisciplinary scientific study
of the mind and its processes. It examines
what

cognition

is, what it does and how it works. It
includes research on intelligence and behavior,
especially focusing on how information is represented,
processed, and transformed (in faculties such as
perception, language, memory, reasoning, and emotion)
within nervous systems (human or other animal) and
machines (e.g. computers).

Thinking humanly: cognitive modeling


1960s "cognitive revolution": information
-
processing
psychology




Requires scientific theories of internal activities of the
brain





--

How to validate? Requires


1) Predicting and testing behavior of human subjects (top
-
down)


or 2) Direct identification from neurological data (bottom
-
up)



Both approaches (roughly, Cognitive Science and
Cognitive Neuroscience)


are now distinct from
AI

Thinking Rationally

The law of thought approach


Thinking rationally means right thinking .

A pattern for argument structure that always gives correct
answers or conclusions

For example

Socrates is a man , all men are mortals, therefore
S
ocrates is
mortal.

These laws of thought were supposed to govern the operations
of mind this initiated the field of logic.

There are two obstacles in this approach

1) But it is a big difference between being able to solve a
problem theoretically and
d
oing it in practice.

2) It is not easy to take informal data and turn into a
frmal

data
specially when the informal data is not 100% certain.

Thinking rationally: "laws of thought"


Aristotle: what are correct arguments/thought processes?




Several Greek schools developed various forms of
logic
:
notation

and
rules of derivation

for thoughts; may or may
not have proceeded to the idea of mechanization




Direct line through mathematics and philosophy to modern
AI




Problems:

1.
Not all intelligent behavior is mediated by logical deliberation

2.
What is the purpose of thinking? What thoughts should I have
?

Acting Rationally

The Rational agent approach


an agent is something that simply acts but computer agents
have more then just acts that made them not just mere
programs

The attributes of a agent are


Operating under autonomous ( self ruling) control


Identifying their environment


Continuing over a prolonged time period


Adjusting to change


Capable of taking on another goal

A
rational agent
acts to get best outcome and under uncertainty
the best expected outcome.


Acting rationally: rational agent



Rational

behavior: doing the right thing




The right thing: that which is expected to
maximize goal achievement, given the available
information




Doesn't necessarily involve thinking


e.g.,
blinking reflex


but thinking should be in the
service of rational action



R
ational agent

A
rational agent
acts to get best outcome and under uncertainty
the best expected outcome.

In the law of thought approach to AI the importance is given on
correct conclusions or outcomes

Making correct conclusions or inferences are a part of being
rational agent.

So one way to act rationally is to reason logically

It has to reason logically for the given conclusions and show that
the action taken will get us the desired goal

Rationality is not only about correct conclusions at times there is
no correct thing to do yet something is to be done,

For example
reflex action
, if I take time in thinking weather to
move my hand from the stove or not then it will be to late ,

At this time some action needs to be taken that’s it

Rational agents


An
agent

is an entity that perceives and acts




This course is about designing rational agents




Abstractly, an agent is a function from percept histories to
actions:



[
f
:
P*



A
]



For any given class of environments and tasks, we seek the
agent (or class of agents) with the best performance




Caveat: computational limitations make perfect rationality
unachievable



design best
program

for given machine resources


R
ational agent involves the Turing test
skills

The rational agent approach takes all the
s
kills needed for the
Turing Test to allow these rational actions to come into being

1)
We need the Knowledge and reason as this helps us in taking
good decisions in a variety of situations ,

2)
We need natural language
prcessor

in order to help us with
complex languages in this complex society

3)
We need visual perception to get a better action , if we see a
nasty pit ahead then we can move away from it to avoid
damage

So the study of AI as a rational approach is more general than
the “ Law of thought approach” as correct conclusions is just one
of the several tools used for achieving rationality


Advantages of the study of AI as Rational
agent design


1)
The study of AI as a rational approach is more general than
the “ Law of thought approach” as correct conclusions is just
one of the several tools used for achieving rationality

2)
This approach is more amenable to scientific development
than compared to other approaches which is based on
human behavior or human thought

As here in this approach the standard of rationality is clearly
defined and completely general.

Whereas in human behavior when in complicated and unknown
evolutionary process still this approach cannot produce
perfection in result , as humans are still good at taking decisions
in a more complex situations and even emotional one.


The Foundation of Artificial Intelligence

Academic Disciplines of AI


Philosophy


Logic, methods of reasoning, mind as physical





system, foundations of learning, language,




rationality
.


Mathematics


Formal representation and proof, algorithms,




computation, (un)decidability, (in)tractability


Probability/Statistics

modeling uncertainty, learning from data



Economics


utility, decision theory, rational economic agents


Neuroscience


neurons as information processing units.



Psychology/

how do people behave, perceive, process cognitive


Cognitive
Science

information, represent knowledge
.



Computer


building fast computers

engineering



Control theory


design systems that maximize an objective




function over time


Linguistics


knowledge representation, grammars