Overview of Artificial Intelligence

What is AI ?

Artificial Intelligence (AI) is a branch of computer science which deals with helping machines finds
solutions to complex problems in a more human-like fashion. Artificial intelligence is based on the
principle that human intelligence can be defined in a way that a machine can easily mimic it and execute
tasks, from the most simple to those that are even more complex. The goals of artificial intelligence
include mimicking human cognitive activity. Researchers and developers in the field are making
surprisingly rapid strides in mimicking activities such as learning, reasoning, and perception, to the extent
that these can be concretely defined. Some believe that innovators may soon be able to develop systems
that exceed the capacity of humans to learn or reason out any subject. But others remain skeptical because
all cognitive activity is laced with value judgments that are subject to human experience.
Artificial Intelligence (AI), a term coined by emeritus Stanford Professor John McCarthy in 1955, was
defined by him as “the science and engineering of making intelligent machines”. Much research has
human’s program machines to behave in a clever way, like playing chess.
“Artificial intelligence is a computerized system that exhibits behavior that is commonly thought of as
requiring intelligence.”
“Artificial Intelligence is the science of making machines do things that would require intelligence if done
by man.”
“AI is the science and engineering of making intelligent machines, especially intelligent computer
programs.”
Artificial intelligence can be viewed from a variety of perspectives.
1. From the perspective of intelligence artificial intelligence is making machines "intelligent" -- acting as
we would expect people to act. The inability to distinguish computer responses from human responses is
called the Turing test. Intelligence requires knowledge. Expert problem solving - restricting domain to
allow including significant relevant knowledge.
2. From a business perspective AI is a set of very powerful tools, and methodologies for using those tools to
solve business problems.
3. From a programming perspective, AI includes the study of symbolic programming, problem solving, and
search. Typically AI programs focus on symbols rather than numeric processing, Problem solving -
achieve goals and search - seldom access a solution directly.
AI language programming
1. Python

1
 Python tends to top the list of best AI programming languages, When it comes to artificial
intelligence, Python comes out strong thanks to its wide variety of pre-designed libraries that are
particularly useful in artificial intelligence development.
1. Java
Java is exceedingly easy to implement on a variety of platforms. This means that once you AI
application is written and compiled on one platform, you can run it on other platforms easily with
the write once run anywhere methodology.
2. R
A number of AI applications involve big data and crunching of big numbers. Did you know that a
special language was developed just for the purpose of statistical computing? That’s right, R was
created by statisticians just for performing computations and crunch massive data sets with ease
in a matter of seconds. Today, R is a powerful language used for machine learning programming
applications, and any artificial intelligence applications that involve extensive computation or
data analysis.
3. C++
C++ rapid processing speed makes it of particular interest to complex machine learning models as it
allows them to run with high efficiency. C++ boasts some extremely useful attributes
4. Julia
Julia is a relatively new AI programming language designed to effectively handle expansive
numerical analysis and handle large data sets with ease. The engineers at MIT designed Julia
keeping in mind all the requirements of modern AI development. It possesses remarkable speed,
powerful computational capacity, easy script like syntax and much more, helping developers
make the best AI programming.
5. Haskell
Haskell’s winning attribute is safety and speed. Haskell is a purely functional, modern AI
programming language with far reaching advantages in Artificial intelligence programming. It has
advanced features such as type classes that enable type-safe operator overloading.
6. Prolog
It is a logical, declarative programming language developed for natural language processing. How
good it is at that job can be understood by the fact that IBM Watson uses Prolog in parsing natural
language in fielding human-generated questions.

Some of the winning attributes that make Prolog a top AI programming language include its
powerful pattern matching, meta level reasoning, and tree-based data structuring. The pattern

2
 matching features has significant importance in natural language processing, computer vision, and
intelligent database search.
7. LISP
LISP is probably the oldest AI programming language. In fact, the very term Artificial Intelligence
was coined by John McCarthy, the inventor of LISP. It is one of the most flexible programming
languages with automatic garbage collection, quick prototyping abilities, dynamic object creation,
and support for symbolic expressions. LISP was used to express the earliest AI programs such as
ELIZA.
8. JAVASCRIPT
Just like Java, JavaScript is also an ideal match for AI development. However, it is used to develop
more secure and dynamic websites. While Python is suitable for developers who don’t like coding,
JavaScript is for those who don’t mind it.
10. Matlab
Application of Artificial intelligence
 Gaming
Artificial intelligence (AI) in computer games covers the behavior and decision-making process of
game-playing opponents. Computer games are also often multiagents, making teamwork, competition,
and modelling key elements to success. In commercial games, such as action games, role-playing
games, and strategy games, the behavior of model is usually implemented as a variation of simple rule-
based systems.
 Speech Recognition

Speech recognition, also known as automatic speech recognition (ASR), computer speech recognition,
or speech-to-text, is a capability which enables a program to process human speech into a written
format. While it’s commonly confused with voice recognition, speech recognition focuses on the
translation of speech from a verbal format to a text one whereas voice recognition just seeks to identify
an individual user’s voice.
 Natural Language processing
Natural language processing (NLP) refers to the branch of artificial intelligence concerned with
giving computers the ability to understand text and spoken words in much the same way human beings
can NLP drives computer programs that translate text from one language to another, respond to spoken
commands, and summarize large volumes of text rapidly even in real time. There’s a good chance

3
you’ve interacted with NLP in the form of voice-operated systems, digital assistants, speech-to-text
dictation software, customer service chat bots.

 Computer Vision

Computer vision is a field of artificial intelligence (AI) that enables computers and systems to derive

meaningful information from digital images, videos and other visual inputs and take actions or make

recommendations based on that information and works much the same as human vision, computer

vision trains machines to perform these functions, but it has to do it in much less time with cameras,

data and algorithms rather than retinas, optic nerves and a visual cortex. At present there are only

limited ways of representing three-dimensional information directly, and they are not as good as what

humans evidently use.

 Expert Systems
An expert system is a computer program that uses artificial intelligence (AI) technologies to
simulate the judgment and behavior of a human or an organization that has expert knowledge and
experience in a particular field. Typically, an expert system incorporates a knowledge base containing
accumulated experience and an inference or rules engine -- a set of rules for applying the knowledge
base to each particular situation that is described to the program. That allows them to improve their
performance based on experience, just as humans do. Expert systems have played a large role in many
industries including in financial services, telecommunications, healthcare, customer service like
MYCIN in 1974v, which helped to identify bacteria such as bacteremia and meningitis, and to
recommend antibiotics and dosages.
 Robotics

Robotics is another field where artificial intelligence applications are commonly used. Robots
powered by AI use real-time updates to sense obstacles in its path and pre-plan its journey
instantly. It can be used for -
Carrying goods in hospitals, factories, and warehouses
Cleaning offices and large equipment
Inventory management
Heuristic Classification
Heuristic classification is suitable for classification problems in which it is known from experience
which observations - or combinations of observations – indicate intermediate or final solutions, and
4
 with what degree of certainty. Thus the basic object types are observations, solutions and rules of
the form "observation indicates solution" (0 →S, with certainty x). That solution is selected which
has the highest total score on the basis of the observations.

Step Problem Solving Process

Six step guide to help you solve problems:

1. Defining The Problem: The definition of the problem must be included precisely. It should
contain the possible initial as well as final situations which should result in acceptable solution.
2. Identification Of Solutions: List all the possible solutions; don’t worry about the quality of the
solutions at this stage.
3. Evaluate alternatives: The next step is to go through and eliminate less desirable or
unreasonable solutions. Evaluate the remaining solutions in terms of their advantages and
disadvantages.
4. Decide on a solution : Specify who will take action.
5. Choosing a Solution: From all the identified solutions, the best solution is chosen basis on the
results produced by respective solutions.
6. Implementation: After choosing the best solution, its implementation is done.
All this steps not available to find the solution in artificial intelligence problems , Since the
choice is made by heuristic, it must be searched using one of the research methods, that is,
finding by inference methods.
Inference

5
It is one of the logical deductions from facts and rules using heuristic. In artificial intelligence, we
need intelligent computers which can create new logic from old logic or by evidence, so generating
the conclusions from evidence and facts is termed as Inference.
Inference rules
Inference rules are the templates for generating valid arguments. Inference rules are applied to derive
proofs in artificial intelligence, and the proof is a sequence of the conclusion that leads to the desired
goal.
In inference rules, the implication among all the connectives plays an important role. Following are
some terminologies related to inference rules:
o Implication: It is one of the logical connectives which can be represented as P → Q. It is a
Boolean expression.
o Converse: The converse of implication, which means the right-hand side proposition, goes to
the left-hand side and vice-versa. It can be written as Q → P and P → Q
o Contrapositive: The negation of converse is termed as contrapositive, and it can be
represented as is Q→P is ¬ Q ¬ P.
o Inverse: The negation of implication is called inverse. It can be represented as
¬ P → ¬ Q is Q→P
From the above term some of the compound statements are equivalent to each other, which we can
prove using truth table:
o Conjunction: The proposition "p and q" denoted by p  q, is true when both p and q are true and is
false otherwise. The proposition p  q is called the conjunction of p and q
Definitions
-Implicit functional association: if the definition of function cannot be expressed briefly and clearly,
the only way to specify the function is by listening all types that satisfy it.
* Clinic (date, time, doctor, patient);
For example: Clinic (1/1/2022, 4PM, Ali, samir);

-Explicit functional association: if the definition of function can be expressed briefly and clearly.
Examples: f(x)=(x-32)/1.8
-Data: is the fundamental, indivisible object in the application.
-Information: is implicit functional association between data in the application.
- Knowledge: is the explicit functional association between item of information and/or data in
the application.

6
 How human solve problem
To solve problem in AI systems try to simulate humans from science of knowledge or
cognitive, which includes the following points:
1. How is knowledge store in human brain?
2. How is knowledge obtained back from brain for process and usage?
3. How is knowledge gained (the mechanism used in gaining knowledge )
4. Problem solving or decision making is process information using the method of qualitative
description or logical deduction.
Conventional programming and intelligence programming
Conventional programming could be assembly language or a high-level language such as C, C++,
Java, JavaScript, Python, etc. Conventional programming is a manual process, which means the
programmer creates the logic of the program. The program processes dependence for data or
information.
Intelligence programming is the simulation of human intelligence processes by machines,
especially computer systems. Specific applications of AI include expert systems, natural language
processing, and speech recognition and machine vision. The program processes dependence for
knowledge

Knowledge process Data process

1, Represent and used knowledge Represent and used data and information
2 It used heuristic processing It used algorithmic processing
3 Inferential process Repetitive processing

. The problem formulation is as follows:

 States: It describes the location of each numbered tiles and the blank tile.
 Initial State: We can start from any state as the initial state.
 Actions: Here, actions of the blank space is defined, i.e., either left, right, up or down
 Transition Model: It returns the resulting state as per the given state and actions.
 Goal test: It identifies whether we have reached the correct goal-state.
 Path cost: The path cost is number of steps in the path where the cost of each step is 1.

Measuring problem-solving performance

There are four ways to measure the performance of an algorithm:

7
1. Completeness: It measures if the algorithm guarantees to find a solution (if any solution exist).
2. Optimality: It measures if the strategy searches for an optimal solution.
3. Time Complexity: The time taken by the algorithm to find a solution.
4. Space Complexity: Amount of memory required to perform a search.