Difference between revisions of "Basics-of-Artificial-Intelligence/C2/Machine-Learning-and-Deep-Learning/English"

From Script | Spoken-Tutorial
Jump to: navigation, search
(Created page with "Spoken Tutorial-AI-2 Introduction to Machine Learning and Deep Learning '''Meta Tags''': AI, Artificial Intelligence, Machine Learning, Deep Learning, Rule-based Programming...")
 
Line 1: Line 1:
−
Spoken Tutorial-AI-2
 
  
−
Introduction to Machine Learning and Deep Learning
+
'''Tutorial Name''': 2. Machine Learning and Deep Learning
  
−
'''Meta Tags''': AI, Artificial Intelligence, Machine Learning, Deep Learning, Rule-based Programming, Neural Networks, Spam Filter, Voice Assistant, Spoken Tutorial, EduPyramids
+
'''Keywords''':
−
 
+
AI, Artificial Intelligence, Machine Learning, Deep Learning, Rule-based Programming,
−
'''Pre-requisite Tutorial''' : '''Introduction to Artificial Intelligence'''
+
Neural Networks, Spam Filter, Voice Assistant, Spoken Tutorial, EduPyramids
  
 +
'''Pre-requisite Tutorial''': Introduction to Artificial Intelligence 
  
 
{|border=1
 
{|border=1
Line 15: Line 15:
 
|| '''Slide 1'''
 
|| '''Slide 1'''
  
−
'''Title slide'''
+
Title slide
  
−
'''Machine Learning and Deep Learning'''
+
Machine Learning and Deep Learning
−
|| Welcome to this Spoken Tutorial on '''Machine Learning and Deep Learning'''.
+
|| Welcome to this '''Spoken Tutorial''' on '''Machine Learning and Deep Learning'''.
 
|-
 
|-
−
|| '''Slide 2 '''
+
|| '''Slide 2'''
  
 
'''Learning Objectives'''
 
'''Learning Objectives'''
 +
Montage of AI tools from previous tutorial
 +
(YouTube, Maps, Photos)
 +
|| In this '''tutorial'', we will learn
 +
About '''Rule-based Programming''', '''Machine Learning''' and '''Deep Learning''', and 
  
−
Montage of AI tools from previous tutorial (YouTube, Maps, Photos)
+
How '''Machine Learning''' and '''Deep Learning''' are connected to '''AI'''.
−
|| In this tutorial, we will learn,
+
−
* About''' Rule-based Programming, Machine Learning''' and '''Deep Learning''', and
+
−
* How '''Machine Learning''' and '''Deep Learning''' are connected to '''AI.'''
+
  
 
|-
 
|-
 
|| '''Slide 3'''
 
|| '''Slide 3'''
−
 
 
'''System Requirements'''
 
'''System Requirements'''
 +
* A '''computer''', a '''laptop''', or a '''smartphone'''
 +
* A stable '''internet''' connection
 +
* An updated '''web browser''', such as '''Google Chrome''', '''Microsoft Edge''', or '''Mozilla Firefox'''
 +
|| You do not need '''coding''' or technical skills.
  
−
|| For this tutorial, you will need:  
+
|-
−
* A computer, a laptop, or a smartphone.
+
|| '''Slide 4'''
−
* A stable internet connection.
+
'''Pre-requisite'''
−
* An updated web browser, such as Chrome, Edge, or Firefox.
+
http://EduPyramids.org
 +
Image/animation: Animated gears or code flow
 +
|| For the pre-requisite '''Artificial Intelligence tutorials''', please visit this '''website'''.
 +
 
 +
Let’s start with understanding '''rule-based programming''' using a real-life example.
  
−
You do '''not''' need coding or technical skills.
 
−
|-
 
−
|| Image/animation: Show '''Animated gears or code flow'''
 
−
|| Let’s start with '''rule-based programming''' using a real-life example.
 
 
|-
 
|-
 
|| Image/animation: Automatic water dispenser with sensor
 
|| Image/animation: Automatic water dispenser with sensor
−
 
 
|| Think about the time you used an automatic water tap.
 
|| Think about the time you used an automatic water tap.
  
−
You place your hand under a water tap.  
+
You place your hand under a water tap.
  
−
The '''sensor''' in the tap detects your hand.  
+
The '''sensor''' in the tap detects your hand.
  
 
Then, it automatically turns on the water tap.
 
Then, it automatically turns on the water tap.
  
 
The water starts flowing.
 
The water starts flowing.
 +
 
|-
 
|-
 
|| Image/animation: Close-up of tap sensor
 
|| Image/animation: Close-up of tap sensor
 +
Zoom in on sensor area; show “Detection = green light”
 +
|| The '''sensor''' follows one rule.
  
−
Zoom in on sensor area; show “Detection = green light
+
“IF a hand is detected under the tap, THEN turn on the water tap.”
−
|| The '''sensor''' follows one rule:
+
  
−
“'''IF''' a hand is detected under the tap, '''THEN''' turn on the water tap.”
 
 
|-
 
|-
−
|| Image/animation: large vessel placed under the tap
+
|| Image/animation: Large vessel placed under the tap
 +
Zoom in on sensor area; show “No Detection”
 +
|| Now, think about what would happen if we placed a large vessel under the tap?
  
−
Zoom in on sensor area; show “ No Detection”
+
The '''sensor''' in the tap will not detect it.
  
−
|| Now, think about what would happen if we placed a large vessel under the tap?
+
This happens because '''rules''' can’t handle new cases.
  
−
The sensor in the tap will not detect it.  
+
They have limitations.
  
−
This happens because''' rules''' can’t handle new cases.
+
They can only follow the exact instructions we give them.
  
−
They have limitations.
 
−
 
−
They can only follow the exact instructions we give them.
 
 
|-
 
|-
−
|| Image/animation:  
+
|| Image/animation:
−
 
+
 
Simple flowchart: Hand detected → Tap on → Water flows
 
Simple flowchart: Hand detected → Tap on → Water flows
−
|| This is '''rule-based programming'''.  
+
|| This is rule-based programming.
 +
 
 +
The '''machine''' simply follows the exact set of instructions given to it.
  
−
The machine simply follows the exact set of instructions given to it.
 
 
|-
 
|-
−
|| Image/animation: : “ Machine Learning”  
+
|| Image/animation: “Machine Learning”
−
|| Now, let’s discuss '''Machine Learning,''' commonly referred to as '''ML'''.
+
|| Now, let’s discuss '''Machine Learning''', commonly referred to as '''ML'''.
 +
 
 
|-
 
|-
 
|| Image/animation: Email inbox with spam and regular mails
 
|| Image/animation: Email inbox with spam and regular mails
−
|| In the '''email inbox''' shown here, do you see a '''folder''' labelled ''''Spam''''?
+
|| In the '''email inbox''' shown here, do you see a '''folder''' labelled '''“Spam”'''?
−
|-
+
−
|| Image/animation: Show Spam folder of an email
+
  
 +
|-
 +
|| Image/animation: Show Spam folder of an email
 
“Data → ML Model → Prediction”
 
“Data → ML Model → Prediction”
 +
|| Your unwanted '''email''' automatically goes into this '''folder.
 +
'''
 +
This sorting happens using '''Machine Learning'''.
  
−
Highlight the suspicious words, links, or senders.
+
|-
−
 
+
|| Image/animation:
−
Image/animation:Highlight spam mails vs regular mails (side by side)
+
Highlight suspicious words, links, or senders
−
 
+
Highlight spam mails vs regular mails
 
Highlight “model” in the diagram
 
Highlight “model” in the diagram
−
|| Your unwanted''' email '''automatically goes into this folder.
+
|| '''ML''' is trained using thousands of '''spam''' and regular '''emails'''.
  
−
This sorting happens using '''Machine Learning.'''
+
From these examples, the '''machine''' learns patterns of what '''spam''' looks like.
  
−
'''ML''' is trained using thousands of '''spam''' and regular '''emails'''.
+
It checks for suspicious words, strange links, and unknown senders.
  
−
From these examples, the machine learns patterns of what spam looks like.
+
Once trained, it can predict whether a new '''email''' is '''spam''' or not.
  
−
It checks for things like suspicious words, strange links, and unknown senders.
 
  
−
Once trained, it can predict whether a new '''email '''is '''spam '''or not.
 
 
|-
 
|-
 
|| Pause icon overlay
 
|| Pause icon overlay
−
|| Pause the''' tutorial '''now.
+
|| Pause the '''tutorial''' now.
 +
Open the '''Spam folder''' in your '''email'''.
  
−
Open the '''Spam''' '''folder''' in your''' email.'''
+
Look at the '''emails''' in this '''folder'''.
  
−
Look at the '''emails '''in this''' folder'''.  
+
They have been separated from your '''inbox''' using '''Machine Learning'''.
  
−
They have been separated from your''' inbox '''using '''Machine Learning.'''
 
 
|-
 
|-
−
|| Transition slide:Deep Learning
+
|| Transition slide: Deep Learning
 
|| Now, let’s go one step deeper into '''Machine Learning''' and understand '''Deep Learning'''.
 
|| Now, let’s go one step deeper into '''Machine Learning''' and understand '''Deep Learning'''.
 +
'''Deep Learning''' is commonly referred to as '''DL'''.
  
−
'''Deep Learning''' is commonly referred to as '''DL.'''
 
 
|-
 
|-
−
|| Visual:  
+
|| Visual: Voice assistant (Google Assistant)
−
* Voice assistant (e.g. Google Assistant / Siri)  
+
Ask: “What is the time in India now?”
−
* what is the time in India now
+
|| Let’s open '''Google Chrome.'''
−
* Show the response
+
  
−
|| Let’s open '''Google Chrome'''.
+
Click on the '''mic icon''' in the '''search bar''' to ask a question in '''voice mode'''.
−
 
+
−
Click on the '''mic icon '''in the''' search bar''' to ask a question in''' voice mode. '''
+
  
 
Then ask, “What’s the time in India now?”
 
Then ask, “What’s the time in India now?”
  
−
It understands and processes the voice input and gives an answer.
+
It understands and processes the voice '''input''' and gives an answer.
  
 
This process happens with the help of '''Deep Learning'''.
 
This process happens with the help of '''Deep Learning'''.
 +
 
|-
 
|-
−
|| '''Visual:''' Illustration of neural network (dots and lines)
+
|| Visual: Neural network illustration
−
 
+
Dots and lines lighting up layer by layer
−
Animation:
+
Text: “Many Layers = Deep Learning”
−
* Small dots connected by lines
+
|| Do you know how '''deep learning''' gave the answer?  
−
* Small dots lighting up like decision nodes
+
−
* Arrows between nodes passing signals
+
−
* Layers lighting up one after another
+
−
* “Many Layers = Deep Learning”
+
−
 
+
−
|| Do you know how deep learning gave the answer?  
+
−
 
+
−
'''Deep Learning''' uses '''artificial neural networks. '''
+
  
−
These networks have many layers that work together.
+
'''Deep Learning''' uses '''artificial neural networks'''.
  
 
You can think of them as many tiny helpers.
 
You can think of them as many tiny helpers.
Line 163: Line 158:
 
As information travels through the layers, the understanding becomes clearer.
 
As information travels through the layers, the understanding becomes clearer.
  
−
Finally, the computer understands your question and gives the right answer.
+
Finally, the '''computer''' understands your question and gives the right answer.
 +
 
 
|-
 
|-
−
|| Visual
+
|| Visual: Face recognition or speech recognition
−
* Layers lighting up one after another
+
|| As there are many layers, we refer to it as '''“deep.”'''
−
* “Many Layers = Deep Learning”
+
−
* Show recognizing faces or understanding speech by computer
+
  
−
|| As there are many layers, we refer to it as "'''deep."'''
+
Each layer helps improve the understanding a little more, like '''building blocks'''.
  
−
Each layer helps improve the understanding a little more, like building blocks.
+
Hence, Deep Learning is used for complex tasks.
−
 
+
−
Hence, '''Deep Learning '''is used for complex tasks.
+
  
 
For example, in understanding speech or recognizing images.
 
For example, in understanding speech or recognizing images.
 +
 
|-
 
|-
−
|| Visual: Russian doll animation: AI (outer) → ML (inner) → DL (innermost)
+
|| Visual: Russian doll animation
−
|| Imagine '''AI, ML''', and '''DL''' like Russian dolls.
+
AI (outer) → ML (middle) → DL (inner)
 +
|| Imagine '''AI, ML,''' and '''DL''' like '''Russian dolls''''''Bold text'''.
  
 
One doll inside the other.  
 
One doll inside the other.  
Line 185: Line 179:
 
First comes '''AI''', the biggest doll.
 
First comes '''AI''', the biggest doll.
  
−
Inside '''AI''' is '''ML''', and inside ML is '''DL.'''
+
Inside '''AI''' is '''ML''', and inside '''ML''' is '''DL'''.
 +
 
 
|-
 
|-
 
|| Visual: Highlight outer doll: AI
 
|| Visual: Highlight outer doll: AI
−
|| '''AI''' is a broad field that makes machines intelligent.  
+
|| '''AI''' is a broad field that makes '''machines''' intelligent.  
  
 
It’s like the outer shell that includes many different methods.
 
It’s like the outer shell that includes many different methods.
 +
 
|-
 
|-
 
|| Visual: Highlight middle doll: ML
 
|| Visual: Highlight middle doll: ML
−
|| '''ML''' is a '''subset '''of''' AI.'''
+
|| '''ML''' is a subset of '''AI'''.
  
−
It learns from data.  
+
It learns from '''data'''.  
  
 
It’s a smaller doll inside '''AI'''.
 
It’s a smaller doll inside '''AI'''.
 +
 
|-
 
|-
 
|| Visual: Highlight inner doll: DL
 
|| Visual: Highlight inner doll: DL
−
|| '''Deep Learning''' is a '''subset '''of '''ML'''.  
+
|| '''Deep Learning''' is a subset of '''ML'''.  
  
 
It is nested inside '''ML'''.
 
It is nested inside '''ML'''.
  
−
It learns from large amounts of data using artificial neural networks.
+
It learns from large amounts of '''data''' using '''artificial neural networks'''.
  
 
This lets it handle complex tasks.
 
This lets it handle complex tasks.
 +
 
|-
 
|-
−
|| '''Summary slide:'''
+
|| '''Summary slide'''
 +
Bulleted list
 +
|| Let’s quickly summarize what we learned.
  
−
'''Bulleted List '''
+
* Rule-based programming follows fixed steps.
−
|| Let’s quickly summarize what we learned in this tutorial.
+
  
−
We learned that:
+
* Machine Learning learns patterns from data.
−
* '''Rule-based programming''' follows fixed steps.
+
 
−
* '''Machine Learning''' learns patterns from data.
+
* Deep Learning uses neural networks with many layers.
−
* '''Deep Learning''' uses neural networks with many layers.
+
 
−
* '''ML''' and '''DL''' are parts of '''AI'''
+
* ML and DL are parts of AI.
  
 
|-
 
|-
 
|| '''Assignment slide'''
 
|| '''Assignment slide'''
−
* Think of an application from your daily life that uses '''fixed rules'''. (This is your rule-based programming example.)
 
−
* Next, think of another application that '''learns from data''' or uses '''Deep Learning'''. (Examples include spam filters, image recognition, or voice assistants.)
 
−
* Write down both examples and explain why each one fits its category.
 
−
 
 
|| Now, here’s a quick assignment for you.
 
|| Now, here’s a quick assignment for you.
  
−
Think of an application from your daily life that uses '''fixed rules.'''
+
Think of an application from your daily life that uses fixed rules.
  
−
Next, think of an application that learns from data or uses deep learning.  
+
Next, think of an application that learns from data or uses Deep Learning.
  
 
Write down both examples and explain why each one fits its category.
 
Write down both examples and explain why each one fits its category.
 +
 
|-
 
|-
 
|| EduPyramids logo
 
|| EduPyramids logo
−
|| This Spoken Tutorial is brought to you by '''EduPyramids Educational Services Private Limited'''.
+
|| This brings us to the end of this tutorial.
 +
 
 +
This Spoken Tutorial is brought to you by EduPyramids Educational Services Private Limited.
 +
 
 
|-
 
|-
 
|| Closing slide
 
|| Closing slide

Revision as of 03:44, 29 December 2025

Tutorial Name: 2. Machine Learning and Deep Learning

Keywords: AI, Artificial Intelligence, Machine Learning, Deep Learning, Rule-based Programming, Neural Networks, Spam Filter, Voice Assistant, Spoken Tutorial, EduPyramids

Pre-requisite Tutorial: Introduction to Artificial Intelligence

Visual Cue Narration
Slide 1

Title slide

Machine Learning and Deep Learning

Welcome to this Spoken Tutorial on Machine Learning and Deep Learning.
Slide 2

Learning Objectives Montage of AI tools from previous tutorial (YouTube, Maps, Photos)

In this 'tutorial, we will learn

About Rule-based Programming, Machine Learning and Deep Learning, and

How Machine Learning and Deep Learning are connected to AI.

Slide 3

System Requirements

  • A computer, a laptop, or a smartphone
  • A stable internet connection
  • An updated web browser, such as Google Chrome, Microsoft Edge, or Mozilla Firefox
You do not need coding or technical skills.
Slide 4

Pre-requisite http://EduPyramids.org Image/animation: Animated gears or code flow

For the pre-requisite Artificial Intelligence tutorials, please visit this website.

Let’s start with understanding rule-based programming using a real-life example.

Image/animation: Automatic water dispenser with sensor Think about the time you used an automatic water tap.

You place your hand under a water tap.

The sensor in the tap detects your hand.

Then, it automatically turns on the water tap.

The water starts flowing.

Image/animation: Close-up of tap sensor

Zoom in on sensor area; show “Detection = green light”

The sensor follows one rule.

“IF a hand is detected under the tap, THEN turn on the water tap.”

Image/animation: Large vessel placed under the tap

Zoom in on sensor area; show “No Detection”

Now, think about what would happen if we placed a large vessel under the tap?

The sensor in the tap will not detect it.

This happens because rules can’t handle new cases.

They have limitations.

They can only follow the exact instructions we give them.

Image/animation:

Simple flowchart: Hand detected → Tap on → Water flows

This is rule-based programming.

The machine simply follows the exact set of instructions given to it.

Image/animation: “Machine Learning” Now, let’s discuss Machine Learning, commonly referred to as ML.
Image/animation: Email inbox with spam and regular mails In the email inbox shown here, do you see a folder labelled “Spam”?
Image/animation: Show Spam folder of an email

“Data → ML Model → Prediction”

Your unwanted email automatically goes into this folder.

This sorting happens using Machine Learning.

Image/animation:

Highlight suspicious words, links, or senders Highlight spam mails vs regular mails Highlight “model” in the diagram

ML is trained using thousands of spam and regular emails.

From these examples, the machine learns patterns of what spam looks like.

It checks for suspicious words, strange links, and unknown senders.

Once trained, it can predict whether a new email is spam or not.


Pause icon overlay Pause the tutorial now.

Open the Spam folder in your email.

Look at the emails in this folder.

They have been separated from your inbox using Machine Learning.

Transition slide: Deep Learning Now, let’s go one step deeper into Machine Learning and understand Deep Learning.

Deep Learning is commonly referred to as DL.

Visual: Voice assistant (Google Assistant)

Ask: “What is the time in India now?”

Let’s open Google Chrome.

Click on the mic icon in the search bar to ask a question in voice mode.

Then ask, “What’s the time in India now?”

It understands and processes the voice input and gives an answer.

This process happens with the help of Deep Learning.

Visual: Neural network illustration

Dots and lines lighting up layer by layer Text: “Many Layers = Deep Learning”

Do you know how deep learning gave the answer?

Deep Learning uses artificial neural networks.

You can think of them as many tiny helpers.

Each helper understands a small part of the voice.

They pass this information from one layer to the next.

As information travels through the layers, the understanding becomes clearer.

Finally, the computer understands your question and gives the right answer.

Visual: Face recognition or speech recognition As there are many layers, we refer to it as “deep.”

Each layer helps improve the understanding a little more, like building blocks.

Hence, Deep Learning is used for complex tasks.

For example, in understanding speech or recognizing images.

Visual: Russian doll animation

AI (outer) → ML (middle) → DL (inner)

Imagine AI, ML,' and DL like Russian dolls'Bold text.

One doll inside the other.

First comes AI, the biggest doll.

Inside AI is ML, and inside ML is DL.

Visual: Highlight outer doll: AI AI is a broad field that makes machines intelligent.

It’s like the outer shell that includes many different methods.

Visual: Highlight middle doll: ML ML is a subset of AI.

It learns from data.

It’s a smaller doll inside AI.

Visual: Highlight inner doll: DL Deep Learning is a subset of ML.

It is nested inside ML.

It learns from large amounts of data using artificial neural networks.

This lets it handle complex tasks.

Summary slide

Bulleted list

Let’s quickly summarize what we learned.
  • Rule-based programming follows fixed steps.
  • Machine Learning learns patterns from data.
  • Deep Learning uses neural networks with many layers.
  • ML and DL are parts of AI.
Assignment slide Now, here’s a quick assignment for you.

Think of an application from your daily life that uses fixed rules.

Next, think of an application that learns from data or uses Deep Learning.

Write down both examples and explain why each one fits its category.

EduPyramids logo This brings us to the end of this tutorial.

This Spoken Tutorial is brought to you by EduPyramids Educational Services Private Limited.

Closing slide Thank you for watching!

Contributors and Content Editors

Madhulika, Madhurig

Retrieved from "https://script.spoken-tutorial.org/index.php?title=Basics-of-Artificial-Intelligence/C2/Machine-Learning-and-Deep-Learning/English&oldid=57297"