Knowledge Based Systems

References
• Artificial Intelligence: A Modern Approach
by Stuart Russell and Peter Norvig
(4th edition), 2020

• Intelligent Systems for Engineers and Scientists

A Practical Guide to Artificial Intelligence
By Adrian A. Hopgood
(4th edition), 2022

Prepared by: Dr. Intessar Al-Iedani 2

Introduction

Artificial Intelligence

Prepared by: Dr. Intessar Al-Iedani 3

 What is Intelligence?
• The “ability to perceive or infer information, and to retain it as knowledge to be applied
towards adaptive behaviors within an environment or context.”

• Ability to interact with the real world

o To perceive, understand and act
Example: Speech Recognition – Understanding and synthesis
Example: Image Recognition
Example: Ability to take action: to have an effect
• Reasoning and planning
o Modelling the external world, given input
Solving new problems, planning and making decisions
Ability to deal with unexpected problems, uncertainties
• Learning and adaptation Prepared by: Dr. Intessar Al-Iedani 4
How do machines become Artificially Intelligent?

• Humans become more and more intelligent with time as they gain experiences
during their lives.
• Similarly, machines also become intelligent once they are trained with some
information which helps them achieve their tasks.
• AI machines also keep updating their knowledge to optimize their output.

Prepared by: Dr. Intessar Al-Iedani 5

 What is Artificial Intelligence AI?
• Describe machines (or computers) that mimic "cognitive" functions that humans associate
with the human mind, such as "learning" and "problem solving”.

A machine is artificially intelligent when:

• A machine possesses the ability to mimic human traits, i.e.,
make decisions, predict the future, learn and improve on its own.
• It can accomplish tasks by itself –
collect data, understand it, analyze it, learn from it, and improve it.

Prepared by: Dr. Intessar Al-Iedani 6

Acting humanly: The Turing test approach

Prepared by: Dr. Intessar Al-Iedani 7

Prepared by: Dr. Intessar Al-Iedani 8
AI Definition by John McCarthy
• John McCarthy (1927-2011)
co-authored the document that coined the term "artificial
intelligence" (AI), developed the Lisp programming language
family.

• Artificial intelligence is the science and engineering of

making intelligent machines, especially intelligent computer
programs

• Intelligence is the computational part of the ability to

achieve goals in the world

Prepared by: Dr. Intessar Al-Iedani 9

 What is not AI?
• Any machine that has been trained with data and can make decisions/ predictions on its own
can be termed as AI. Here, the term ‘training’ is important.
• A fully automatic washing machine can work on its own, but it requires human intervention
to select the parameters of washing and to do the necessary preparation for it to function
correctly before each wash, which makes it an example of automation, not AI.
• An air conditioner can be turned on and off remotely with the help of internet but still needs a
human touch. This is an example of Internet of Things (IoT).
• robots which might follow a path or maybe can avoid obstacles but need to be primed
accordingly each time.
• lot of projects which can automate our surroundings with the help of sensors. Here too, since
the bot or the automation machine is not trained with any data, it does not count as AI.

Prepared by: Dr. Intessar Al-Iedani 10

Applications of Artificial Intelligence around us

Prepared by: Dr. Intessar Al-Iedani 11

Applications of Artificial Intelligence around us

Prepared by: Dr. Intessar Al-Iedani 12

AI, ML & DL Artificial Intelligence (AI): any technique that enables
computers to mimic human intelligence. It gives the ability to
machines to recognize a human’s face; to move and manipulate
objects; to understand the voice commands by humans, and
also do other tasks.

Machine Learning (ML): It is a subset of Artificial

Intelligence. The technologies and algorithms that enables
systems to identify patterns, make decisions, and improve
themselves through experience and data.

Deep Learning (DL): Is a subset of machine learning that uses

complex algorithms and deep artificial neural networks to train
a model. The learning enables software to train itself to perform
tasks with vast amounts of data. Deep Learning is the most
advanced form of Artificial Intelligence out of these three.

Prepared by: Dr. Intessar Al-Iedani 13

Categories of AI software
• Research into AI, together with other branches of computer science, has resulted in the
development of several useful computing tools that can be roughly divided between
• knowledge-based systems (KBSs),
• computational intelligence (CI),
• hybrid systems.
KBSs include: CI includes:
• Expert systems, • Neural networks,
• Rule-based systems, • Genetic algorithms,
• Frame-based systems, • Other optimization algorithms.
• Intelligent agents,
• Case-based reasoning.

• Techniques for handling uncertainty, such as fuzzy logic, fit into both categories.
Prepared by: Dr. Intessar Al-Iedani 14
Categories of AI software

Prepared by: Dr. Intessar Al-Iedani 15