Artificial intelligence

Artificial intelligence (AI) is the ability of a computer or a robot controlled by a computer to do tasks that are
usually done by humans because they require human intelligence and discernment. Although there are no AIs
that can perform the wide variety of tasks an ordinary human can do, some AIs can match humans in specific
tasks.

Concept of AI
What are the Fundamental AI Concepts?
To fully understand how AI works, you need to learn about the following basic concepts first:

1. Machine Learning
In the simplest terms, machine learning (ML) is a subset of AI. Its core lies in the idea that computer systems
can learn on their own from data obtained from performing previous tasks and past experiences. That means
that you don’t have to pre-program an AI device every time you need it to work on a job.

ML has three subcategories—supervised, unsupervised, and reinforcement.

Supervised learning occurs when an AI system arrives at a predictable conclusion based on existing data.

Unsupervised learning, meanwhile, takes place when the AI agent produces an unpredictable result, which it
was not pre-trained to do.

Reinforcement learning (also known as “goal-oriented programming”) deals with training the AI algorithm to
recognize rewards and punishments so that it can come up with the best solution to a problem.

2. Deep Learning
This subset of AI refers to a system’s ability to take unstructured data from multiple sources, analyze it, and
apply it to solve new problems. Deep learning is also known as “differential programming.”

This web-like structure of artificial neural networks means that they are able to process data in a non-linear
approach, which is a significant advantage over traditional algorithms.

3. Artificial neural network (ANN)

Artificial neural network refers to a system or an algorithm used in deep learning that mimics how the human
brain’s neural circuits function, such as when making sense of things and events.

Some of the most popular examples of NLP applications are Alexa from Amazon and Siri from Apple.
4. Reinforcement learning
Reinforcement learning is a part of Artificial Intelligence in which the machine learns something in a way that is
similar to how humans learn. As an example, assume that the machine is a student. Here the hipothetical
student learns from its own mistakes over time through trial and error.

This means that the algorithm decides the next action by learning behaviours that are based on its current state
and that will maximise the reward in the future.

A famous example of Reinforcement Learning is Google’s alpha Go computer Programme that was able to beat
the world champion in the game of Go in 2017.

5 Robotics
Robotics is a field that deals with creating humanoid machines that
can behave like humans and perform some actions like human
beings. Now, robots can act like humans in certain situations but can they think like humans as well? This is
where artificial intelligence
comes in! Al allows robots to act intelligently in certain situations.
These robots may be able to solve problems in a limited sphere or
even learn in controlled environments.

An example of this is Kismet, which is a social interaction robot

developed at MIT’s Artificial Intelligence Lab. It recognizes the
human body language and also our voice and interacts with humans
accordingly. Another example is Robonaut, which was developed by
NASA to work alongside the astronauts in space.

Techniques of Artificial Intelligence

1. Machine Learning
It is one of the applications of AI where machines are not explicitly programmed to perform certain tasks;
rather, they learn and improve from experience automatically. Deep Learning is a subset of machine learning
based on artificial neural networks for predictive analysis. There are various machine learning algorithms, such
as Unsupervised Learning, Supervised Learning, and Reinforcement Learning. In Unsupervised Learning, the
algorithm does not use classified information to act on it without any guidance. In Supervised Learning, it
deduces a function from the training data, which consists of a set of an input object and the desired output.
Reinforcement learning is used by machines to take suitable actions to increase the reward to find the best
possibility which should be taken in to account.

2. NLP (Natural Language Processing)

It is the interactions between computers and human language where the computers are programmed to
process natural languages. Machine Learning is a reliable technology for Natural Language Processing to obtain
meaning from human languages. In NLP, the audio of a human talk is captured by the machine. Then the audio
to text conversation occurs, and then the text is processed where the data is converted into audio. Then the
machine uses the audio to respond to humans.

Applications of Natural Language Processing can be found in IVR (Interactive Voice Response) applications used
in call centres, language translation applications like Google Translate and word processors such as Microsoft
Word to check the accuracy of grammar in text.

However, the nature of human languages makes the Natural Language Processing difficult because of the rules
which are involved in the passing of information using natural language, and they are not easy for the
computers to understand. So NLP uses algorithms to recognize and abstract the rules of the natural languages
where the unstructured data from the human languages can be converted to a format that is understood by
the computer.

3. Automation and Robotics

The purpose of Automation is to get the monotonous and repetitive tasks done by machines which also
improve productivity and in receiving cost-effective and more efficient results. Many organizations use machine
learning, neural networks, and graphs in automation. Such automation can prevent fraud issues while financial
transactions online by using CAPTCHA technology. Robotic process automation is programmed to perform high
volume repetitive tasks which can adapt to the change in different circumstances.

4. Machine Vision
Machines can capture visual information and then analyze it. Here cameras are used to capture the visual
information, the analogue to digital conversion is used to convert the image to digital data, and digital signal
processing is employed to process the data. Then the resulting data is fed to a computer. In machine vision,
two vital aspects are sensitivity, which is the ability of the machine to perceive impulses that are weak and
resolution, the range to which the machine can distinguish the objects. The usage of machine vision can be
found in signature identification, pattern recognition, and medical image analysis, etc.
Characteristics of AI applications Problem Solving
https://studyresearch.in/2018/03/11/characteristics-of-ai-problems/

https://www.nitsri.ac.in/Department/Computer%20Science%20 HYPERLINK
"https://www.nitsri.ac.in/Department/Computer Science & Engineering/ProblemSolving(L-2).pdf"& HYPERLINK
"https://www.nitsri.ac.in/Department/Computer Science & Engineering/ProblemSolving(L-
2).pdf"%20Engineering/ProblemSolving(L-2).pdf

What is Production System?

A production system is based on a set of rules about behavior. These rules are a basic representation found
helpful in expert systems, automated planning, and action selection. It also provides some form of artificial
intelligence.

Production system or production rule system is a computer program typically used to provide some form of
artificial intelligence, which consists primarily of a set of rules about behavior but it also includes the
mechanism necessary to follow those rules as the system responds to states of the world.

Components of Production System

The major components of Production System in Artificial Intelligence are:

Global Database: The global database is the central data structure used by the production
system in Artificial Intelligence.

Set of Production Rules: The production rules operate on the global database. Each rule
usually has a precondition that is either satisfied or not by the global database. If the precondition is satisfied,
the rule is usually be applied. The application of the rule changes the database.

A Control System: The control system then chooses which applicable rule should be applied and
ceases computation when a termination condition on the database is satisfied. If multiple rules are to fire at
the same time, the control system resolves the conflicts.

Features of Production System in Artificial Intelligence

1. Simplicity: The structure of each sentence in a production system is unique and uniform as they
use the “IF-THEN” structure. This structure provides simplicity in knowledge representation. This feature of the
production system improves the readability of production rules.
2. Modularity: This means the production rule code the knowledge available in discrete pieces.
Information can be treated as a collection of independent facts which may be added or deleted from the
system with essentially no deleterious side effects.

3. Modifiability: This means the facility for modifying rules. It allows the development of
production rules in a skeletal form first and then it is accurate to suit a specific application.

4. Knowledge-intensive: The knowledge base of the production system stores pure

knowledge. This part does not contain any type of control or programming information. Each production rule is
normally written as an English sentence; the problem of semantics is solved by the very structure of the
representation.

Production System Rules

Production System rules can be classified as:

Deductive Inference Rules

Abductive Inference Rules

You can represent the knowledge in a production system as a set of rules along with a control system and
database. It can be written as:

If(Condition) Then (Condition)

The production rules are also known as condition-action, antecedent-consequent, pattern-action, situation-
response, feedback-result pairs.

Forward Chaining and backward chaining in AI

Forward chaining is known as data-driven technique because we reaches to the goal using the available data.

Backward chaining is known as goal-driven technique because we start from the goal and reaches the initial
state in order to extract the facts

https://www.educba.com/forward-chaining-vs-backward-chaining/