Artificial Intelligence
Presented By:
Ch.Anjana Priya
!4A81A05D2
Sri Vasavi Engg Clg
Contents
Overview
Applications
Language
s
A.I. Introduction
Introduction
Claiming to be able to recreate the
capabilities of the human mind, is both a
challenge and an inspiration for philosophy.
It is the science and engineering of making
intelligent machines, especially intelligent
computer programs.
Are there limits to how intelligent machines can
be?
Intelligence:
the capacity to learn and solve problems
Artificial Intelligence:
Artificial intelligence(AI) is
theintelligenceof machines and robots
and the branch ofcomputer science
that aims to create it
the ability to solve problems
the ability to act rationally
the ability to act like humans
Philosophy of A.I.
Searle's
strong AI hypothesis:
"The appropriately programmed
computer with the right inputs
& outputs would thereby have a
mind in exactly the same sense
human beings have minds."
The artificial brain argument:
The brain can be simulated.
Technologically feasible to copy
the brain directly into hardware
and software, and that such a
simulation will be essentially
identical to the original.
History of artificial intelligence
Classical
philosophers
Programmable Digital Computers
(1940)
1943-1956:
McCulloch & Pitts: Boolean circuit
model of brain
Dartmouth meeting: "Artificial
Intelligence name adopted
The
golden years 19561974
1986--
Rise of machine learning
Neural networks return to popularity
Major advances in machine learning
algorithms and applications
1995--
AI as Science
Integration of learning, reasoning,
knowledge representation
AI methods used in vision, language,
data mining, etc
2006:
face recognition software
available in consumer cameras
2003-2007 Robot driving: DARPA
grand challenge
Feb
2011 there came question
answering robot.
Can AI System
Work As
Efficient As
Human
How
complicated is our brain?
Neuron
10 12 neurons in a human brain
many more synapses (10 14) connecting these
neurons
cycle time: 10 -3 seconds (1 millisecond)
How
complex can we make
computers?
108 or more transistors per CPU
supercomputer: hundreds of CPUs, 1012 bits of RAM
cycle times: order of 10 - 9 seconds
Conclusion
YES
Less interconnections (wires or synapses)
Faster
Languages
Artificial intelligence researchers have developed
several specialized programming languages for artificial
intelligence which include IPL, Lisp, Prolog, STRIPS,
Planner, POP-11 etc.
LISP (Introduction)
Lisp is a family of computer
programming languages with a
long history and a distinctive, fully
parenthesized Polish prefix
notation.
The name LISP derives from "List
Processing". Linked lists are one of
Lisp languages' major data
structures, and Lisp source code is
itself made up of lists. As a result,
Lisp programs can manipulate
source code as a data structure,
giving rise to the macro systems
that allow programmers to create
new syntax or even new domainspecific languages embedded in
Lisp.
LISP (Syntax &
Semantics)
Lisp is an expression-oriented
language. Unlike most other languages,
no distinction is made between
"expressions" and "statements"; all
code and data are written as
expressions. McCarthy's 1958 paper
introduced two types of syntax:
S-expressions (Symbolic
expressions)
(car (cons A B))
M-expressions (Meta Expressions)
car[cons[A,B]]
LISP connection to A.I.
LISP is an important language for
artificial Intelligence programming.
LISP programs define how to perform
an algorithm on the expressions.
Frames, networks and objects are
responsible for LISPs popularity in the
AI community.
Lisp is widely used in implementing
the tools of Artificial Intelligence.
PROLOG (Introduction)
Prolog is a general purpose logic programming language
associated with AI and computational linguistics.
Prolog has its roots in first-order and formal logic.
It is declarative and expressed in terms of relations,
represented as facts and rules.
PROLOG (Syntax &
Semantics)
In Prolog, program logic is expressed in terms of
relations, and a computation is initiated by running
a query over these relations.
In syntax and semantics following are considered:
Data types
Rules and facts
Evaluation
Loops
Negation
PROLOG (Data Types)
An atom, whose meanings is not defined.
Numbers can be floats or integers.
Variables are strings consisting of letters, numbers
and underscore characters, and beginning with an
upper-case letter or underscore(_).
Comparison
LISP
PROLOG
Functional language
Logical language
General purpose
Specific uses
Handles wide variety of tasks,
easier to use
Smaller language, easier to learn
Dnt support compared to prolog
Supports multidirectional
reasoning
Parent disciplines of AI:
It is a broad field with so many
subareas.
Applications of AI:
Natural
Language
Understanding
Expert Systems
Planning and Robotics
Machine Learning
Game Playing
Natural Language
Processing
To
design and build software that
will analyze understand and
generate languages that human
use naturally.
Modes of communication
Text
based.
Dialogue
based.
Speech Recognition
Process
of converting sound
signal captured by microphone or
mobile/telephone to a set of
words.
70-100
of 90%
words / min with accuracy
Computer Vision
Ability
of a machine to extract
information from an image that is
necessary to solve a task
Image
Acquisition
Image Processing
Image Analysis
Image understanding
Intelligent Robot
Tend
to mimic
human sensing
and decision
making abilities
so that they can
adopt
themselves to
certain
conditions and
modify their
actions.
Expert Systems
These
are
Softwares used
for decision
making .
Automated
Reasoning and
Theorem
Proving.
Troubleshooting
Expert Systems.
Stock Market
Expert System.
Artificial Intelligence the need of
hour
"Many
thousands of AI
applications are deeply
embedded in the infrastructure of
every industry."
The late 90s and early 21st
century, AI technology became
widely used as elements of larger
systems,but the field is rarely
credited for these successes.
Fields of AI
Computer science:
Graphical
User Interface
Automatic Storage management
Object Oriented Programming
Data miming
computer gaming
Telecommunication:
Automated Online Assistants
Voice dialing
Speech Recognization
Fields of AI
Aviation &
Automation:
NASA's fight research
centre
Voice recognition in
fighter jets
Directions to A.I pilots
through air traffic
controllers
Automatic Gearing
System in Cars
Fields of AI
Robotics:
Assembling
Robots
Welding Robots
Behavior based
robotics
Dancing Robots
Robot navigation
Daily life applications
Home
Security
Bank
Post
office
Websites
Digital cameras
News and
publishing
Financial trades
Health and
medicine
Games and toys
different????????
Artificial Intelligence
Natural Intelligence
Non Creative
Creative
Precise
May Contain Error
Consistency
Non Consistent
Multitasking
Cant Handle
Drawbacks of A.I
Limited
Ability
Slow Real Time
Response
Cant Handle
Emergency
Situation
Difficult code
High Cost
Any
Questio
ns
Thanks