Skip to main content

What is Machine Learning?

Objective​

This chapter explains machine learning in a simple and understandable way. You will learn what it is, how it works, and the difference between it and regular programming.

1. Simple Definition​

What is Machine Learning?​

Machine Learning is a method by which a computer learns from data without the need for explicit programming for each task.

Simple Example:

  • Instead of programming the computer for everything
  • We give it data and a result
  • It learns by itself how to connect them

Simple Analogy​

Regular Programming:

  • Like giving a child detailed instructions
  • "If you see a cat, say 'cat'"
  • "If you see a dog, say 'dog'"

Machine Learning:

  • Like teaching a child with pictures
  • Show them thousands of pictures of cats and dogs
  • They learn the difference by themselves

2. How Does It Work?​

Simple Process​

Step 1: Data

  • We need a lot of data
  • For example: thousands of pictures of cats

Step 2: Training

  • The computer analyzes the data
  • Discovers patterns

Step 3: Learning

  • Learns from the patterns
  • Builds its own understanding

Step 4: Application

  • Uses what it learned
  • On new data

3. Practical Example: Cat Recognition​

How Does the Computer Learn?​

1. Data:

  • 10,000 pictures of cats
  • 10,000 pictures of other things

2. Training:

  • The computer analyzes the pictures
  • Looks for common patterns in cat pictures

3. Learning:

  • Learns: cats have pointed ears
  • Learns: cats have tails
  • Learns: cats have certain eyes

4. Application:

  • New picture
  • The computer examines it
  • Says: "This is a cat" or "This is not a cat"

4. Difference Between Regular Programming and Machine Learning​

Regular Programming​

How It Works:

  • The programmer writes specific instructions
  • The computer follows the instructions
  • The result is predetermined

Example:

If the number is greater than 10:
    print "Large"
Else:
    print "Small"

Machine Learning​

How It Works:

  • We give the computer data
  • It discovers the rules by itself
  • The result is not predetermined

Example:

  • We give it thousands of pictures
  • It discovers how to recognize cats
  • Without programming the rules

5. Why is Machine Learning Important?​

Advantages​

1. Flexibility:

  • Adapts to new data
  • Does not need new programming

2. Continuous Learning:

  • Improves over time
  • Learns from mistakes

3. Handling Complexity:

  • Can handle complex problems
  • Difficult to program in the usual way

4. Discovery:

  • Discovers patterns we did not notice
  • New ideas

6. Where Do We Find Machine Learning?​

In Our Daily Lives​

In Phones:

  • Face recognition
  • Word suggestions
  • Voice assistants

In Shopping:

  • Product recommendations
  • Product recognition

In Entertainment:

  • Video recommendations
  • Sound and image enhancement

In Medicine:

  • Analyzing medical images
  • Assisting in diagnosis

In Cars:

  • Smart cars
  • Obstacle recognition

7. What Does Machine Learning Need?​

Requirements​

1. Data:

  • A lot of data
  • High-quality data

2. Computing Power:

  • Powerful computers
  • To analyze data

3. Time:

  • Training takes time
  • Sometimes hours or days

4. Expertise:

  • Expertise in machine learning
  • To build good models

Conclusion​

  • Machine learning is a method by which a computer learns from data
  • Does not need explicit programming for each task
  • Present everywhere in our lives
  • Learns from data and improves its performance