Artificial intelligence (AI) involves creating intelligent machines that can perform tasks requiring human intelligence. This document discusses the history and development of AI including conventional AI methods like expert systems and computational intelligence methods like neural networks. It provides examples of applications of AI like game playing, speech recognition, natural language processing, computer vision, and expert systems. Overall, the document provides a comprehensive overview of the field of AI, its methods and applications.

1. ARTIFICIAL INTELLIGENCE
ABSTRACT:
Artificial intelligence is exhibited by artificial entity, a system is generally assumed to be
a computer. AI systems are now in routine use in economics, medicine, engineering and the
military, as well as being built into many common home computer software applications,
traditional strategy games like computer chess and other video games.
It cleared the concept of computational and conventional categories. It includes various
advanced systems such as Neural Network, Fuzzy Systems and Evolutionary computation. AI is
used in typical problems such as Pattern recognition, Natural language processing and more.
This system is working throughout the world as an artificial brain.
Intelligence involves mechanisms, and AI research has discovered how to make
computers carry out some of them and not others.
We can learn something about how to make machines solve problems by observing other
people or just by observing our own methods. On the other hand, most work in AI involves
studying the problems the world presents to intelligence rather than studying people or animals.
AI researchers are free to use methods that are not observed in people or that involve much more
computing than people can do.
Although AI has a strong science fiction connotation, it forms a vital branch of
computer science, dealing with intelligent behavior, learning and adaptation in machines.
Research in AI is concerned with producing machines to automate tasks requiring intelligent
behavior. Examples include control, planning and scheduling, the ability to answer diagnostic
and consumer questions, handwriting, speech, and facial recognition. As such, it has become a
scientific discipline, focused on providing solutions to real life problems. AI systems are now in
routine use in economics, medicine, engineering and the military, as well as being built into
many common home computer software applications, traditional strategy games like computer
chess and other video games.
CONTENT:
1

2. History:
The intellectual roots of AI, and the concept of intelligent machines, may be
found in Greek mythology. Intelligent artifacts appear in literature since then, with real
mechanical devices actually demonstrating behaviour with some degree of intelligence. After
modern computers became available following World War-II, it has become possible to create
programs that perform difficult intellectual tasks. It was started from 1950 onwards.
Categories of AI:-
AI divides roughly into two schools of thought:
• Conventional AI.
• Computational Intelligence (CI).
• Conventional AI:-
It involves methods now classified as machine learning, characterized by
formalism and statistical analysis. This is also known as symbolic AI, logical AI, neat AI
and Good Old Fashioned Artificial Intelligence (GOFAI).
Methods include:
• Expert systems: apply reasoning capabilities to reach a conclusion. An expert
system can process large amounts of known information and provide
conclusions based on them.
• Case based reasoning.
• Bayesian networks.
• Behavior based AI: a modular method of building AI systems by hand.
• Computational Intelligence (CI):-
It involves iterative development or learning (e.g. parameter tuning e.g. in
connectionist systems). Learning is based on empirical data and is associated with non-
symbolic AI, scruffy AI and soft computing.
Methods include:
• Neural networks: systems with very strong pattern recognition capabilities.
2

3. • Fuzzy systems: techniques for reasoning under uncertainty, has been widely
used in modern industrial and consumer product control systems.
• Evolutionary computation: applies biologically inspired concepts such as
populations, mutation and survival of the fittest to generate increasingly better
solutions to the problem. These methods most notably divide into
evolutionary algorithms (e.g. genetic algorithms) and swarm intelligence (e.g.
ant algorithms).
Genetic Algorithms GA’s – What are they?
Genetic Algorithms are based on the principles of survival of the fittest; sometimes called
natural selection. GA’s, informally, work as follows.
Many potential solutions to the problem are created. Each solution is evaluated to see
how good it is. The best solutions are allowed to breed with each other.
This cycle continues in the hope that, as we are breeding with the good solutions, we will
gradually breed better and better solutions. And the evidence supports that this is the case for a
wide variety of problems. As GA’s have their origins in genetics the terms have carried through
into the computer counterparts.
Each solution is normally called a chromosome (or an individual). Each chromosome is
made up of genes, which are the individual elements that represent the problem. The collection
of chromosomes is called a population.
In a problem such as the travelling salesman problem (TSP) the genes would be
individual cites. A chromosome would be a complete tour and the population would be a number
of complete tours.
As stated above, GA’s work by breeding the best individuals from the current population.
Let’s consider this is a bit more detail.
It is common to have a population of one hundred. We’ll work with that figure for now.
The initial population of one hundred chromosomes is normally created randomly. Many
problems are represented as bit strings, but this need not be the case and other representations
have been used.
3

4. The individuals that make up the population are then evaluated. That is, some function considers
each chromosome and assigns it a value depending on how good an answer it is to the problem.
The chromosomes are then allowed to breed. But what does this mean?
Firstly we need to choose suitable “parents.” Overall we want to choose the fittest
members of the population to breed but, as in life, everybody must be given the chance to breed.
Just because an individual has a low evaluation does not mean he/she does not have something to
contribute to society.
Therefore, in choosing parents, it is normally done in such a way that they are chosen in
proportion to their evaluation rating. In doing this the fitter individuals are more likely to breed
but the weaker members of the population also have the opportunity.
Having chosen our parents we now allow them to breed. This means (normally) two
offspring are produced from the two parents. The children consist of genetic material taken from
both parents. How the genetic material is distributed can be done in a number of ways, which we
discuss below.
However, we do not breed all the time. There is a probability associated with each
breeding pair as to whether they produce children or not. The probability of breeding is usually
set to something like sixty percent but other figures are often experimented with.
Occasionally, as in life, a mutation occurs and GA’s also mimic this.
Mutation happens with low probability and how the mutation occurs depends on the coding that
is being used. If the problem is being represented by bit strings then mutation is fairly easy to
implement. It can simply look at each bit in the chromosome and decide (with some low
probability) if the bit should be replaced with a randomly produced bit.
The last point that should be made about GA’s is that they have no knowledge about the
problem it is trying to solve. The only part of the GA that has some domain knowledge is the
evaluation function. This function is given a chromosome and passes back an evaluation for the
chromosome. It is this evaluation rating that the breeding mechanism uses in deciding which
chromosomes should breed.
The breeding mechanism has no knowledge about the problem. In its simplest form a GA
is just manipulating bit strings.
4

5. GA Algorithm:
A Genetic Algorithm can be implemented using the following outline algorithm
1. Initialize a population of chromosomes
2. Evaluate each chromosome (individual) in the population
2.1. Create new chromosomes by mating chromosomes in the current population (using
crossover and mutation)
2.2. Delete members of the existing population to make way for the new members
2.3. Evaluate the new members and insert them into the population
3. Repeat stage 2 until some termination condition is reached (normally based on time or
number of populations produced)
4. Return the best chromosome as the solution.
This is the basic GA algorithm. As we shall see below there are many parameters that we can
use to affect this basic algorithm.
Typical problems to which AI methods are applied:-
• Pattern recognition
o Optical character recognition
o Handwriting recognition
o Speech recognition
o Face recognition
• Natural language processing, Translation and Chatter bots
• Non-linear control and Robotics
• Computer vision, Virtual reality and Image processing
• Game theory and Strategic planning.
Other fields in which AI methods are implemented:-
• Automation.
• Cybernetics.
• Hybrid intelligent system.
5

6. • Intelligent agent.
• Intelligent control.
• Automated reasoning.
• Data mining.
• Behavior-based robotics.
• Cognitive robotics.
• Developmental robotics.
• Evolutionary robotics.
• Chatbot.
• Knowledge Representation.
Applications of AI:-
1. Game Playing:-
You can buy machines that can play master level chess for a few hundred dollars.
There is some AI in them, but they play well against people mainly through brute force
computation--looking at hundreds of thousands of positions.
2. Speech Recognition:-
In the 1990s, computer speech recognition reached a practical level for limited
purposes. Thus United Airlines has replaced its keyboard tree for flight information by a
system using speech recognition of flight numbers and city names. It is quite convenient.
On the other hand, while it is possible to instruct some computers using speech, most
users have gone back to the keyboard and the mouse as still more convenient.
3. Understanding Natural Language:-
Just getting a sequence of words into a computer is not enough. Parsing sentences
is not enough either. The computer has to be provided with an understanding of the
domain the text is about, and this is presently possible only for very limited domains.
4. Computer Vision:-
The world is composed of three-dimensional objects, but the inputs to the human
eye and computer’s TV cameras are two dimensional. Some useful programs can work
solely in two dimensions, but full computer vision requires partial three-dimensional
information that is not just a set of two-dimensional views. At present there are only
6

7. limited ways of representing three-dimensional information directly, and they are not as
good as what humans evidently use.
5. Expert Systems:-
A knowledge engineer'' interviews experts in a certain domain and tries to
embody their knowledge in a computer program for carrying out some task. How well
this works depends on whether the intellectual mechanisms required for the task are
within the present state of AI. One of the first expert systems was MYCIN in 1974, which
diagnosed bacterial infections of the blood and suggested treatments. It did better than
medical students or practicing doctors, provided its limitations were observed.
REFERENCES:
• www.whatis.com
• www.wikipedia.com
• www.extremetech.com
7