Scribd
Upload
7 views3 pages

Lect - 01 Introduction To Machine Learning

Machine Learning (ML) is a subset of Artificial Intelligence that enables computers to learn from data and make predictions without explicit programming. The process involves data collection, training a model to identify patterns, learning from errors, and making predictions on new data. Real-life applications include spam detection in Gmail, recommendations on streaming services, and fraud detection in banking.

Uploaded by

anmol198395 anmol198395
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
7 views3 pages

Lect - 01 Introduction To Machine Learning

Machine Learning (ML) is a subset of Artificial Intelligence that enables computers to learn from data and make predictions without explicit programming. The process involves data collection, training a model to identify patterns, learning from errors, and making predictions on new data. Real-life applications include spam detection in Gmail, recommendations on streaming services, and fraud detection in banking.

Uploaded by

anmol198395 anmol198395
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

🔹 What is Machine Learning?

Machine Learning (ML) is a branch of Artificial Intelligence (AI) that allows computers to
learn from data and make predictions or decisions without being explicitly programmed.

Instead of writing step-by-step rules, we give the computer data and let it discover the rules
(patterns) itself.

How ML Works:

1. Data Collection – The computer is provided with a dataset containing examples of the
problem it needs to solve.
2. Training – An ML model is created and trained using this data. The model identifies
patterns and relationships.
3. Learning – The model improves by adjusting its parameters based on errors and
feedback.
4. Prediction – Once trained, the model can make decisions or predictions on new, unseen
data.
Simple Example

Imagine teaching a child to recognize apples 🍎 and oranges 🍊.

 You show them many examples (training data).


 They learn patterns (apples are red/round, oranges are orange/rough).
 Next time they see a fruit, they can guess correctly (prediction).

That’s exactly how machine learning works!

🔹 Example (Traditional Programming vs Machine Learning)

 Traditional Programming:
o Rules + Data → Output
o Example: If marks ≥ 50 → Pass, else Fail
 Machine Learning:
o Data + Output → Rules (Model learns automatically)
o Example: Feed in student study hours (X) and exam results (Y). The computer
learns the relationship and can predict results for new students.

🔹 Key Idea

 Computer learns patterns from past data (training).


 Then, it uses those patterns to predict new, unseen cases (testing).

🔹 Simple Real-Life Examples


 Gmail detecting spam emails.
 Netflix or YouTube recommending movies/videos.
 Self-driving cars learning to drive from camera and sensor data.
 Banks detecting fraudulent transactions.

👉 So, in one line:


Machine Learning = Teaching computers to learn from experience (data) and improve
automatically.

You might also like