Unit-1:

Introduction of Artificial
Intelligence
What is Artificial Intelligence (AI)?
Artificial -> “Man Made”
Intelligence -> “Thinking Power”
Artificial Intelligence: It is branch of computer science by which we can create intelligent
machine which can behave like a human, think like human and able to make decisions.
Why Artificial Intelligence (AI)?
With the help of AI, we can create such software or device, which can solve real-world problems
very easily and achieved high accuracy such as health issues, marketing, traffic issues etc.
With the help of AI, you can create your personal virtual assistant, such as google assistant, siri
etc.
With the help of AI, you can build such robots which can work in a environment where survival
of human can be at risk.
AI opens a path for new technologies, new devices and new opportunities.
Goal of Artificial Intelligence (AI)
Replicate Human Intelligence
Solve knowledge-intensive tasks
Building a machine which can perform tasks that requires human intelligence such as:
Providing a theorem
Playing chess
Plan some surgical operation
Driving a car in traffic
Problem Solving
Problem solving in games such as “Sudoku”.
It can be done by building an AI system to solve that particular problem.
E.g. Problem Solving Techniques:
Chess
Travelling sales man problem
Tower of Hanoi problem
Water Jag problem
N-Queen problem
Problem Searching
In general, Searching refer to as finding information one needs.
Searching is the most commonly used technique of problem solving in AI.
The process of solving a problem consists of 5 steps:
Define the problem
Analyzing the problem
Identification of solution
Choosing the solution
Implementation
AI Techniques
There are three important AI techniques:
1. Search –
Provides a way of solving problems for which no direct approach is available.
It also provides a framework into which any direct techniques that are available can be embedded.
2. Use of knowledge –
Provides a way of solving complex problems by exploiting the structure of the objects that are involved.
3. Abstraction –
Provides a way of separating important features.
It hide the detail of something.
E.g. If we want to compute the square root of a number then we simply call the function sqrt in C. we do not
need to know the implementation details of this function. Sqrt(3)
Application Domains of AI
Natural Language Processing

Email Spam Filter in Gmail Neural Network

Image Processing
Face Detection in Camera Deep Learning
Speech Recognition
Voice Technology in Virtual Agents Deep Learning
Data Mining

Market Basket Analysis Product recommendation

Expert System

IBM Watson Reinforcement Learning

Robotics

Home Automation Deep Learning

Scheduling
Aurora - Advanced Intelligent
Resource Scheduling Planning and Scheduling Solution
Optimization
Shortest Path Google map path planner
Game Playing

Alpha Go Deep Neural Network

Virtual Agents

Chatbots Conversational AI
Personalized Recommender Systems
Online Shopping Machine Learning
Automated Control Systems

Washing Machine Fuzzy Logic

Security

NVIDIA Metropolis Machine Learning

AI – ML – DL and Data Science
Technique that enables
machines to mimic human
behavior
AI
Subset of AI which uses
Machine statistical methods to enable
Learning machine to learn and improve
Data with time

Science
Deep Subset of ML that includes
Learning algorithms and enables
system to train itself
Advantages of Artificial Intelligence

Solving new problems

Better handling of information
Conversion of information into knowledge
Disadvantages of Artificial Intelligence

Increased costs
Difficulty with software development - slow and expensive
Few experienced programmers
Few practical products have reached the market as yet.
Search
Search is the fundamental technique of AI.
Possible answers, decisions
Search is either "blind" or “uninformed":
blind
▪ we move through the space without worrying about what is coming next, but recognising the answer if we see it
informed
▪ we guess what is ahead, and use that information to decide where to look next.
We may want to search for the first answer that satisfies our goal, or we may want to keep searching until we find
the best answer.
Weak AI
It’s also known as narrow AI or artificial narrow intelligence (ANI).
Weak AI refers to any AI tool that focuses on doing one task really well. That is, it has a narrow scope in terms of
what it can do. 
The idea behind weak AI isn’t to mimic or replicate human intelligence. Rather, it’s to simulate human behavior.
The smartest seeming AI of today are only weak AI.
 “specialized AI” due to its ability to perform very specialized tasks — much of the time even more successfully
than humans.
EXAMPLES OF WEAK AI
Chatbots
Spotify shuffle
Email spam filters
Smart assistants like Siri, Alexa and Cortana
Self-driving cars
Google maps
Apple autocorrect
Strong AI
It is also known as general AI or artificial general intelligence (AGI).
Strong AI refers to AI that exhibits human-level intelligence. So, it can understand, think, and act the
same way a human might in any given situation.
In theory, then, anything a human can do, a strong AI can do too.
We don’t yet have strong AI in the world; it exists only in theory.
This is artificial intelligence that is capable of behaving and performing actions in the same ways human
beings can.
Strong AI is a hypothetical concept which does not exist yet in its true form.
Strong AI VS Weak AI
Weak AI Strong AI
Weak AI models intelligent human behavior, which allows General AI is currently hypothetical concept.
machines to solve complex problems.
Narrow AI is programmed to operate within a set of pre-defined Strong AI will have a mind of its own to be able to accomplish
functions to solve. any type of task
Weak AI does not achieve self-awareness. Strong AI will be advanced enough to be considered truly
intelligent and fully self-aware.
Narrow AI classifies data. General AI uses clustering and association.
Turing Test in AI

Interrogator: Are you a computer?

Player A (Computer): No
Interrogator: Multiply two large numbers such as (256896489*456725896)
Player A: Long pause and give the wrong answer.
From the above example, if the interrogator fails to differentiate between the computer and the human, then
player x (the computer) will have passed the test successfully.
Requirements for passing the Turing test in AI
To pass the test, a machine must meet the following requirements:
Natural language processing (NLP): It can understand natural human languages.
Knowledge representation (KR): The ability of the machine to store and retrieve information.
Automated reasoning (AR): This requires that a machine can use the stored information to
answer questions and make new conclusions.
Machine learning: This requires various machine learning techniques and algorithms.
Limitations of Turing test
The test requires physical interaction.
The test is not reproducible. It uses a different code or logic from the original.
It cannot be performed in an open place since one of its requirements is that the players should
be in separate rooms to ensure they are hidden from view.
The test is limited to analyzing human-like intelligence.
Agents and Environments
Agent
An agent is anything that can perceive its environment through sensors and acts upon that
environment through effectors.
A human agent has sensory organs such as eyes, ears, nose, tongue and skin parallel to
the sensors, and other organs such as hands, legs, mouth, for effectors.
A robotic agent replaces cameras and infrared range finders for the sensors, and various
motors and actuators for effectors.
A software agent has encoded bit strings as its programs and actions.

Structure of an AI Agent
Agent = Architecture + Agent program  
Environment
An environment is everything in the world which surrounds the agent, but it is not a part of an
agent itself. An environment can be described as a situation in which an agent is present.
The environment is where agent lives, operate and provide the agent with something to sense
and act upon it.
Properties of Environment
Discrete / Continuous − If in an environment there are a finite number of actions that can be performed within it, then such an environment is
called a discrete environment else it is called continuous environment. A chess game comes under discrete environment as there is a finite
number of moves that can be performed. A self-driving car is an example of a continuous environment.
Observable / Partially Observable − If it is possible to determine the complete state of the environment at each time point it is observable;
otherwise it is only partially observable.
Static / Dynamic − If the environment does not change while an agent is acting, then it is static; otherwise it is dynamic.
Single agent / Multiple agents − If only one agent is involved in an environment, and operating by itself then such an environment is called
single agent environment. However, if multiple agents are operating in an environment, then such an environment is called a multi-agent
environment.
Accessible / Inaccessible − If an agent can obtain complete and accurate information about the state's environment, then such an environment
is called an Accessible environment else it is called inaccessible. An empty room whose state can be defined by its temperature is an example
of an accessible environment. Information about an event on earth is an example of Inaccessible environment.
Deterministic / Non-deterministic − If the next state of the environment is completely determined by the current state and the actions of the
agent, then the environment is deterministic; otherwise it is non-deterministic.
Known / Unknown - In a known environment, the results for all actions are known to the agent. While in unknown environment, agent needs to
learn how it works in order to perform an action.
Rationality
Rationality is nothing but status of being reasonable, sensible, and having good sense of
judgment.
Rationality is concerned with expected actions and results depending upon what the agent has
performed.
Rational Agent:
A rational agent can be anything that makes decisions.
A rational agent always performs right action.
Rational agent is capable of taking best possible action in any situation.
Example of rational action performed by any intelligent agent:
Automated Taxi Driver:
Performance Measure: Safe, fast, legal, comfortable trip, maximize profits.
Environment: Roads, other traffic, customers.
Actuators: Steering wheel, accelerator, brake, signal, horn.
Sensors: Cameras, sonar, speedometer, GPS, odometer, engine sensors, keyboard.
Thank You!