You are on page 1of 25

Artificial Intelligence

Artificial Intelligence
The theory and development of computer
systems able to perform tasks that normally
require human intelligence, such as visual
perception, speech recognition, decisionmaking, and translation between languages

Computational Intelligence
Is a set of computer based
methodologies used to
solve complex, real-world
problems to which
traditional methodologies
are unfeasable or
ineffective through the use
of Artificial Neural
Networks, Evolutionary
Computation and Fuzzy
Logic systems.

Turing Test
In his 1950 paper
"Computing Machinery
and Intelligence" Alan
Turing proposed the
Turing test in Artificial
Intelligence.

Turing Test
The "standard
interpretation" of the Turing
Test, in which player C, the
interrogator, is tasked with
trying to determine which
player - A or B - is a
computer and which is a
human. The interrogator is
limited to only using the
responses to written
questions in order to make
the determination.

CAPTCHA
"Completely Automated Public Turing test to
tell Computers and Humans Apart"
A CAPTCHA or Captcha is a type of challengeresponse test used in computing to ensure that
the response is not generated by a computer. It
is more commonly used when creating and
signing in to accounts

AI Techniques - Heuristics

AI Techniques - Heuristics
"Rule of Thumb"
Educated Guess
Common Sense

AI Techniques - Heuristics
In computing heuristics search for solutions and
ignore whether the solution can be proved.
Improvements in performance and simplicity
are gained at the cost of accuracy.

AI Techniques - Heuristics
Many anti virus programs use heuristic
methods to search for viruses or malware by
detecting known patterns or behaviour.

AI Techniques - Pattern Recognition


Pattern Recognition is the assignment of output
values to given input values.
Pattern Recognition Uses:
Speech recognition
Handwriting recognition for post codes (OCR)
Face recognition
Image analysis

AI Techniques - Machine Learning


Machine learning is an artificial technique that
make it possible for machine performance to
improve based on feedback from past
performance.
Searching is an AI technique wherein the
computer looks ahead at

FUZZY LOGIC

Fuzzy Logic does not require precise inputs,


is inherently robust, and can process any
reasonable number of inputs but system
complexity increases rapidly with more inputs
and outputs.
Simple, plain-language IF X AND Y THEN Z
rules are used to describe the desired system
response in terms of linguistic variables rather
than mathematical formulas.
The number of these is dependent on the
number of inputs, outputs, and the designer's
control response goals.
http://www.seattlerobotics.org/encoder/mar98/fuz/fl_part2.html#SUMMARY

Fuzzy logic; examples


- Maintaining of ideal temperature in
greenhouses
- Rice Cooker, uses fuzzy logic to cook the rice
for the right amount of time, taking into account
temperature of the room and the humidity
- Cranes use fuzzy logic to control the sway of
the cargo being transported.

Fuzzy Logic - Greenhouse


IF temperature is cold AND getting colder
THEN heat rapidly.
IF temperature is cold AND maintaining THEN
heat slightly
IF temperature is ok AND maintaining, THEN
do nothing.

Fuzzy Logic - Fan


IF temperature IS very cold THEN stop fan
IF temperature IS cold THEN turn down fan
IF temperature IS normal THEN maintain level
IF temperature IS hot THEN speed up fan

Pattern
Recognition

OCR
Optical Character Recognition (OCR) is a
software technology that can convert images of
text into an actual text file that can then be
edited, e.g. using word-processing software).
The result is just as if the text had been typed
in by hand.

OCR is typically used after a page of a


book has been scanned. The scanned
image of the page is then analysed by the
OCR software which looks for
recognisable letter shapes and generates
a matching text file.
Advanced OCR software can recognise
normal handwriting as well as printed text
- this is usually called handwriting
recognition.

OCR Before and After

OCR Before and After

Image Analysis
Image analysis is the extraction of meaningful
information from images; mainly from digital
images by means of digital image processing
techniques. Image analysis tasks can be as
simple as reading bar coded tags or as
sophisticated as identifying a person from their
face.

Speech recognition
Speak recognition converts spoken words to
text.

You might also like