Introduction to Artificial intelligence

1. Fundamentals of AI
& Cyber Security
23ESCC106

2. Course Learning Objectives
This course intends
1. To provide an insight about basic concepts of Artificial Intelligence
and workflow of Intelligent Agents.
2. To impart knowledge of machine learning and its applications.
3. To familiarize Cyber Crimes and Security mechanisms.

3. Syllabus

4. Syllabus

5. Syllabus

6. Syllabus

7. Syllabus

8. Course Outcomes
Student will be able to:
CO1. Understand the workflow of agents in Artificial Intelligence and
design intelligent agent for problem solving.
CO2. Illustrate the concepts of Machine Learning, Applications and its
advantages over human learning.
CO3. Analyze the cybercrimes on digital platform and articulate
defense mechanism for cyber attacks.

9. Google Classroom Class code

10. Module 01
Overview of Artificial Intelligence

13. Introduction to AI
Artificial Intelligence:
“AI refers to systems that simulate human intelligence to
perform tasks like reasoning, learning, and problem-solving.”
• To do tasks that require human Intelligence

14. Introduction to AI
Reasons for Automation of Human Intelligence
• Understand human intelligence better
• Smarter Programs
• Useful techniques for solving difficult problems

15. Introduction to AI
Common man’s Understanding about AI
Artificial: Made as a copy of something natural.
Intelligence: The ability to gain and apply knowledge and skills.

16. Introduction to AI
Technical Person considers AI as follows:
• Wide field of science and engineering which makes
intelligent machines and especially intelligent computer
programs.
• AI is related to the similar task of using computers to
understand human intelligence.

17. What is Intelligence?
Intelligence is a property of mind that encompasses many
related mental abilities, such as the capabilities to
• Reason
• Plan
• Solve problems
• Think abstractly
• Comprehend ideas and language
• Learn

18. Introduction to AI
•Most work in AI involves studying the problems the
world presents to intelligence rather than studying
people or animal.
•AI researchers are free to use methods that are not
observed in people or that involve much more
computing than people can do.

19. Introduction to AI
Tasks that require Intelligence:

Speech Recognition and understanding
• Pattern Recognition
• Mathematical Theorem Proving
• Reasoning
• Motion in obstacle filled space

22. Introduction to AI
Intelligence Artificial Intelligence
Natural Programmed by Human Beings
Increases with experience and also hereditary Nothing called hereditary but systems do learn from
experience.
Highly refined and no electricity from outside is required
to generate the output. Rather knowledge is good for
intelligence
It is in computer system and we need electrical
energy to get output. Knowledge base is required to
generate output.
No one is an expert. We can always get better solution
from another human being.
Expert systems are made which have the capability
of many individual person’s experiences and ideas.
Intelligence increases by supervised or unsupervised
teaching
We can increase AI’s capability by other means
apart from supervised and unsupervised teaching.

29. Introduction to AI
Strong AI Weak AI
Computers can be made to think on a level at least
equal to humans.
Simply states that some “thinking-like” features can be
added to computers to make them more useful tool.
Research deals with the creation of some form of
computer-based AI that can truly reason and solve
problems.
Research deals with the creation of some form of computer-
based artificial intelligence which can reason and solve
problems in a limited domain.
People advocating strong AI believe that it will
eventually lead to computers whose intelligence will
greatly exceed than that of human beings.
Machine would act in some ways as if it is intelligent but it
would not possess true intelligence
The programs are themselves the explanations. Goal is to build machines that help people in their
intellectual tasks.
Goal is to build machines that do the intellectual tasks.

31. Introduction to AI
Definitions of AI
“The art of creating machines that perform functions
that require intelligence when performed by people”
(Kurzweil 1990).
“The branch of computer science that is concerned
with automation of intelligent behaviour”.
(Luger and Stublefield, 1993)

34. Introduction to AI
AI has the following Properties:
Systems that think like humans. Systems that think /rationally
Systems that act like humans Systems that act rationally

35. AI
Acting
humanly
Thinking
rationally
Acting
rationally
Thinking
humanly

38. Introduction to AI

41. Introduction to AI
Acting Humanly: The Turing Test
If the response of a computer to an unrestricted textual natural-
language cannot be distinguished from that of a human being then it
can be said to be intelligent.

42. Introduction to AI
• The Loebner Prize is an annual competition that aims to test artificial
intelligence systems based on the principles of the Turing Test,
developed by Hugh Loebner in 1990.
• The competition rewards AI programs that can best imitate human
behavior in conversation, thus coming closest to passing the Turing
Test.

43. Introduction to AI
Thinking Humanly: Cognitive Modelling
• Method must not just exhibit behaviour sufficient to fool a human judge but
must do it in a way demonstrably analogous to human cognition.
• Requires detailed matching of computer behaviour and timing to detailed
measurements of human subjects gathered in psychological experiments.
• Cognitive Science: Interdisciplinary field(AI, psychology, linguistics,
philosophy, anthropology) that tries to form computational theories of
human cognition,

44. Introduction to AI
Thinking Rationally: Laws of thought
• Formalize “correct” reasoning using a mathematical model(example of
deductive reasoning)
• Logicit Program: Encode knowledge in formal logical statements and use
mathematical deduction to perform reasoning:
• Problems:
• Formalizing common sense knowledge is difficult.
• General deductive inference is computationally intractable

45. Introduction to AI
Acting Rationally: Rational Agents
• An agent is an entity that perceives its environment and is able to execute
actions to change it.
• Agents have inherent goals that they want to achieve (e.g. survive,
reproduce).
• A rational agent acts in a way to maximize the achievements of its goals.
• True maximization of goals requires omniscience and unlimited
computational abilities.
• Limited rationality involved maximizing goal within the computational and
other resources available.

46. Introduction to AI
Many disciplines contribute to a foundation for artificial
intelligence
• Philosophy: logic, philosophy of mind, philosophy of science,
philosophy of mathematics
• Mathematics: logic, probability theory, theory of computability
• Psychology: behaviorism, cognitive psychology
• Computer Science and Engineering: hardware, algorithms,
computational complexity theory
• Linguistics: Theory of grammar, syntax, semantics

61. Application Areas of AI
•Artificial Intelligence (AI)
has a wide range of
applications across various
fields.
•Each application area
leverages AI to solve
problems, automate tasks,
and create intelligent
systems.

62. Application Areas of AI
Artificial Intelligence
General
Problem
Solving
Expert System
Natural
Language
Processing
Computer
Vision
Robotics Others

63. Application Areas of AI
General Problem Solving
• Definition: AI helps in general problem-
solving by simulating human decision-making
processes.
• Examples: Planning algorithms, optimization
problems, and autonomous decision-making.
• Applications: Healthcare, finance, logistics,
and education.

64. Application Areas of AI
Expert Systems
• Definition: Expert systems are AI programs
that mimic the decision-making abilities of
a human expert.
• Examples: Medical diagnosis systems,
troubleshooting systems, and risk analysis
tools.
• Applications: Medical diagnosis (e.g., IBM
Watson), financial advisory systems, and
technical support.

65. Application Areas of AI
Natural Language Processing (NLP)
• Definition: NLP allows AI systems to
understand, interpret, and generate
human language.
• Examples: Chatbots, speech recognition,
language translation, and sentiment
analysis.
• Applications: Virtual assistants (e.g., Siri,
Alexa), customer service bots, and
automated translations.
Application Areas of AI
Application Areas of AI
Application Areas of AI

66. Application Areas of AI
Computer Vision
• Definition: Computer Vision enables AI
systems to analyze and understand visual
information from the world.
• Examples: Image recognition, facial
recognition, object detection.
• Applications: Self-driving cars, medical
image analysis, surveillance systems, and
augmented reality.

67. Application Areas of AI
Robotics
• Definition: Robotics uses AI to design and
control robots that can perform tasks
autonomously or semi-autonomously.
• Examples: Industrial robots, humanoid
robots, drones.
• Applications: Manufacturing, exploration
(e.g., Mars rovers), military applications, and
service industries.

68. Application Areas of AI
Other Applications of AI:
• Gaming: AI is used for creating
intelligent characters and game
mechanics.
• Finance: AI algorithms are used
for stock trading, fraud detection,
and market analysis.
• Cybersecurity: AI identifies
threats and automates security
processes.

74. Comparison of Conventional and AI Computing
•What is Conventional Computing? Based on pre-
programmed algorithms and rules.
•Follows a linear and logical approach to problem-
solving.
•Uses traditional programming techniques where the
system operates based on clearly defined inputs and
outputs.

75. Comparison of Conventional and AI Computing
•What is AI Computing? Involves systems that can
learn, adapt, and make decisions based on data.
•Focuses on emulating human intelligence processes,
like learning, reasoning, and problem-solving.
•Relies on machine learning, neural networks, and deep
learning.

76. Comparison of Conventional and AI Computing
Aspect
Conventional
Computing
AI Computing
Approach Rule-based
Data-driven and
learning-based
Adaptability Fixed instructions
Learns and adapts over
time
Problem Solving Predefined algorithms
Dynamic decision-
making
Human-like
capabilities
None
Emulates human
reasoning
Core Differences

77. Comparison of Conventional and AI Computing
Conventional Computing Characteristics:
• Based on strict logic and arithmetic operations.
• Programs perform tasks only as they are coded.
• Does not handle uncertainty or incomplete information well.
• Example: Calculator or standard desktop applications.

78. Comparison of Conventional and AI Computing
AI Computing Characteristics:
• Utilizes data and statistical models to improve accuracy over time
• Can handle incomplete or uncertain data
• Develop models can that generalize across new situations
• Example: Self-driving cars, Language Translation Systems

79. Comparison of Conventional and AI Computing
Advantages of AI Computing Over Conventional
Computing
• Ability to handle vast amounts of unstructured data.
• Self-improvement through learning.
• Decision-making in complex and dynamic environments.
• Better at mimicking human behavior in tasks like speech recognition, image
processing, etc.

80. Comparison of Conventional and AI Computing
Limitations of AI Computing
• Requires large datasets for training.
• Often operates as a black box (lack of transparency in decision-making).
• High computational power requirements.
• Potential biases if the training data is biased.

82. INTELLIGENT AGENTS
• The word agent is derived from the concept of agency which
means employing someone to act on behalf of the user.
• An agent is something that can be viewed as perceiving its
environment through sensors and acting upon that environment
through actuators
• A human agent has eyes, ears and other organs for sensors and
body parts like hands, legs, mouth, etc for actuators

83. INTELLIGENT AGENTS

85. • A computer agent or software agent represents a person and interacts
with others to accomplish a predefined task
• Computer agents have several characteristics which distinguish them from
mere programs. They are:

Capability to work on their own

Perceiving the environment

Persisting over a prolonged time period

Adapting to change

Capable of taking on another’s goal

Transportable over networks

Ability to interact with humans, systems and other agents

Ability to learn

86. They are:

Capability to work on their own

Perceiving the environment

Persisting over a prolonged time period

Adapting to change

Capable of taking on another’s goal

Transportable over networks

Ability to interact with humans, systems and other
agents

Ability to learn

88. Working Principle

89. In AI, an agent is a system adhering to the PEAS model. Here’s what the model is all about:
Performance measure: A metric evaluating the AI agent’s success in achieving goals
Environment: The world the agent interacts with, perceived through sensors
 Actuators: Mechanisms the agent uses to affect the environment
 Sensors: Methods for gathering information about the environment
AI agents leverage techniques like machine learning, NLP, reasoning, and knowledge
representation to perceive, decide, and act upon their environment to achieve specific
goals.

90. Types of AI Agents

92. Simple Reflex Agents

94. Model-based Reflex Agents

96. Goal-based Agents

98. Utility-based Agents

100. Learning Agents

102. INTELLIGENT AGENTS
• In AI, we use the term INTELLIGENT AGENT which represents a new
technology for software programs
• A good definition of an Intelligent Agent is :
“An intelligent agent is a software entity which senses its own
environment and then carries out some set of operations on
behalf of a user (or a program), with some degree of
autonomy, and in doing so employs some knowledge or
representation of user’s goals or desires.”

103. UNIT TEST
Course Name: Fundamentals of AI & Cyber Security
Course Code: 23ESCC106

104. 1.Define Artificial Intelligence and discuss its primary goals. How does
AI differ from traditional programming?
2.Compare human intelligence with artificial intelligence. Discuss two
strengths of human intelligence and two areas where computers excel
over humans.
3. List and describe five different application areas of AI, explaining
how AI contributes uniquely to each field.
4.Describe any three types of intelligent agents, providing examples of
where each type might be used in real-world applications.