2. ο§ INTODUCTION OF AI
ο§ EVOLUTION OF A.I.
ο§ BRANCHES AND APPLICATIONS OF A.I
ο§ WHAT WE ACHIEVED IN A.I.
ο§ CONCLUSION
3. ο Artificial- Not natural
ο Intelligence- Capability to learn and take
decisions
ο A.I. is a branch of computer science that studies
the computational requirements for tasks such as
perception, reasoning and learning and develop
systems to perform those tasks.
4. ο In the beginning the focus of AI
research was on modelling the human
brain. (This was impossible).
ο John McCarthy term first artificial
intelligence.
ο Research shifted to using games like
noughts and crosses, drafts etc to create
βAIβ systems.
ο The games had a number of rules that were
easy to define.
5. ο In 1965 Researchers agreed that game playing
programs could not pass the Turing test
ο The focus shifted to language processing
ο ELIZA (1966)
ο 1st language processing program
ο Responded to users inputs by asking questions
based on previous responses
ο PARRY (1972)
ο Parry modelled a conversation with a paranoid person
ο This seems odd but the program was created by a
psychiatrist
6. ο The Turing test is a test of a machine's ability to exhibit
intelligent behavior. In Turing's original illustrative
example, a human judge engages in a natural
language conversation with a human and a machine
designed to generate performance indistinguishable from
that of a human being. All participants are separated from
one another. If the judge cannot reliably tell the machine
from the human, the machine is said to have passed the
test. The test does not check the ability to give the correct
answer; it checks how closely the answer resembles typical
human answers. The conversation is limited to a text-only
channel such as a computer keyboard and screen so that
the result is not dependent on the machine's ability to
render words into audio.
7. ο ARTIFICIAL NUERAL SYSTEM
ο COMPUTER VISION
ο NATURAL LANGUAGE PROCESSING (N.L.P)
ο MACHINE LEARNING
ο ROBOTICS
8. ο ANS is an approach to AI where the developer attempts to model the
human brain
ο Simple processors are interconnected in a way that simulates the
connection of nerve cells in the brain
Advantages & Disadvantages of ANS-
Advantages
They can learn without needing to be reprogrammed
Disadvantages
Time consuming and requires a lot of technical expertise to
set up
Canβt tell the reason behind the decision.
9.
10. ο Stages ο Difficulties with
1. Input Image using Digital
Camera Vision Systems
2. Detect Edges of Object
3. Compare to Knowledge ο Shadows on Objects
Base β Pattern Matching ο Identifying the Edge of the
ο Uses Image
ο Security systems, recognizing ο Glare
faces at airports ο Objects hiding other parts
ο Inspection of manufactured of the Image
goods judging quality of ο Viewing from different
production angles
ο Vision systems on automated
cars
ο Interpretation of Satellite
photos for military use
13. ο NLP or Speech Recognition is where an AI system can
be controlled and respond to verbal commands
ο Examples
ο Speech-driven word processors
ο Military weapon control
ο Mobile phones(SIRI)
ο Customer query lines
15. ο What is learning-
βTo gain knowledge or understanding of, or skill in
by study, instruction or experience''
ο Learning a set of new facts
ο Learning HOW to do something
ο Improving ability of something already learned
ο What is machine learning-
``Learning denotes changes in the system that are
adaptive in the sense that they enable the system to do
the same task or tasks drawn from the same population
more effectively the next time''
16. ο Rote learning β One-to-one mapping from inputs to
stored representation. βLearning by memorization.β
Association-based storage and retrieval.
ο Induction β Use specific examples to reach general
conclusions
ο Clustering β Unsupervised identification of natural
groups in data
ο Analogy β Determine correspondence between two
different representations
ο Discovery β Unsupervised, specific goal not given
ο Genetic algorithms β βEvolutionaryβ search techniques,
based on an analogy to βsurvival of the fittestβ
ο Reinforcement β Feedback (positive or negative reward)
given at the end of a sequence of steps
17. ο Robots can be considered intelligent when they go
beyond simple sensors and feedback (dumb robots),
and display some further aspect of human-like
behaviour
ο Vision Systems
ο The ability to learn and improve performance
ο Robot that can walk rather than on wheels
ο NLP response
ο Examples
ο The delivery of goods in warehouses
ο The inspection of pipes
ο Bomb Disposal
ο Exploration of Ocean floor or space
18. ο ASIMO has the ability to recognize moving objects,
postures, gestures, its surrounding environment,
sounds and faces, which enables it to interact with
humans also determine distance and direction. This
feature allows ASIMO to follow a person, or face
him or her when approached. The robot interprets
voice commands and human hand movements,
enabling it to recognize when a handshake is
offered or when a person waves or points, and then
respond accordingly. ASIMO's ability to distinguish
between voices and other sounds allows it to
identify its companions. ASIMO is able to respond
to its name and recognizes sounds associated with a
falling object or collision. This allows the robot to
face a person when spoken to or look towards a
sound. ASIMO responds to questions by nodding
or providing a verbal answer and can recognize
approximately 10 different faces and address them
by name.
19. β’ Stanley is
an autonomous vehicle created
by Stanford University's Stanford Racing
Team in cooperation with
the Volkswagen Electronics Research
Laboratory (ERL). It competed in, and
won, the 2005 DARPA Grand
Challenge, earning the Stanford Racing
Team the 2 million dollar prize, the
largest prize money in robotic history.
Stanley was characterized by a machine
learning based approach to obstacle
detection. To process the sensor data and
execute decisions, Stanley was equipped
with six low-power 1.6 GHz
Intel Pentium M based computers in the
trunk, running different versions of
the Linux operating system.
20. ο Stanford's Autonomous
Helicopter project pushes the
limits of autonomous flight
control by teaching a computer to
fly a competition-class remote
controlled (RC) helicopter
through a range of aerobatic
stunts. The only helicopter that
can hover inverted. Our
apprenticeship learning approach
learns to fly the helicopter by
observing human demonstrations
and is capable of a wide variety of
expert maneuvers. In many cases,
it can even exceed the
performance of the human expert
from which it learned.
21. ο Watson is an artificial intelligence computer
system capable of answering questions posed
in natural language, developed in IBM's Deep
QA project by a research team led
by principal investigator David Ferrucci.
Watson was named after IBM's first
president, Thomas J. Watson.
ο In 2011, as a test of its abilities, Watson
competed on the quiz show Jeopardy!, in the
show's only human-versus-machine match-
up to date. In a two-game, Watson beat Brad
Rutter, the biggest all-time money winner on
Jeopardy!, and Ken Jennings, the record
holder for the longest championship streak
(74 wins).Watson received the first prize of $1
million, while Ken Jennings and Brad Rutter
received $300,000 and $200,000, respectively
22. ο The European research project
ALEAR (Artificial Language
Evolution on Autonomous
Robots), carried out by Dr.
Manfred .Myon is an 1.25 meters
humanoid robot. It was revealed
to the public for the first time at
the International Design Festival
DMY and the Institute for
Advanced Study Berlin
(Wissenschaftskolleg Berlin) and
it caused an extremely high
interest. autonomous robots
move.
23. ο Kismet is a robot made in
the late 1990s
at Massachusetts Institute
of Technology by
Dr. Cynthia Breazeal. The
robot's auditory, visual and
expressive systems were
intended to allow it to
participate in human social
interaction and to
demonstrate simulated
human emotion and
appearance.
24. ο Finally we can say that Artificial intelligence (AI) is
the intelligence of machines and the branch
of computer science that aims to create it. AI textbooks
define the field as "the study and design of intelligent
agentsβ where an intelligent agent is a system that
perceives its environment and takes actions that
maximize its chances of success. John McCarthy, who
coined the term in 1955, defines it as "the science and
engineering of making intelligent machines