Introduction of Machine Learning

 

Machine learning :

•        Machine learning is a field of computer science that uses statistical techniques to give computer systems the ability to "learn” with data, without being explicitly/traditional programmed.

•      Machine learning is technology which enables computers to learn automatically from past data and building model and predict output for future value.

•        In simple word machine learning is all about learning from data

Explicitly / Traditional Programming:

 

Traditional (Explicit / Conventional) Programming

·        Explicitly / traditionally programmed means writing a separate program or logic for every possible scenario.

·        The programmer manually defines rules and conditions.

·        Flow:

o   Logic (Program) + Data → Output

o   The computer only follows the instructions written by the programmer.

o   If a new scenario occurs, the program must be modified.

Example : Fan Control

·        If temperature > 30 → Turn ON fan

·        If temperature ≤ 30 → Turn OFF fan

Machine Learning

·        In machine learning, we do not write logic manually.

·        Instead, we provide:

o   Data (inputs + outputs)

o   Machine learning algorithm

·        The algorithm analyzes the data, identifies patterns, and automatically creates logic.

·        Flow:

o   Data + Algorithm → Model (Learned Logic)

o   New Data → Output

·        Once trained, the model can handle new and unseen scenarios.

Example : Fan Control

·        Provide past temperature data along with fan ON/OFF status

·        The model learns when to turn the fan ON or OFF automatically

 

******************** >< ********************

How Does Machine Learning Work?

Machine Learning Working Diagram :

This diagram explains how a Machine Learning model works from training to final decision.

Step 1: Data Set

• We start with a Dataset.
• It contains historical data.
• In Machine Learning, data can be:
• Numbers (marks, salary, age)
• Categories (Yes/No, Spam/Not Spam)
• Structured data (tables)

- Example: Student marks and Pass/Fail result.

Step 2: Machine Learning Algorithm (Training Phase)

The dataset is given to the Machine Learning Algorithm.

Examples of ML algorithms:

• Linear Regression
• Logistic Regression
• Decision Tree
• SVM

During training:

• The algorithm finds patterns.
• It reduces prediction error.

-  The model learns from past data.

Step 3: Model Creation

After training:

• A Machine Learning Model is created.
• It contains learned patterns.
• It is ready to predict new data.

Step 4: New Input Data

Now we provide:

• New unseen data.

Example:

• New student marks.
• New customer details.

This data goes into the trained ML algorithm.

 Step 5: Prediction

The model processes the new data and gives:

🔎 Prediction

Example:

• Pass / Fail
• Loan Approved / Rejected
• Spam / Not Spam

 Step 6: Decision / Evaluation

On the right side:

• 👍 means correct prediction
• 👎 means wrong prediction
• 🔍 means evaluation

We check:

• Is prediction correct?
• What is the accuracy?

If wrong:
-  Retrain or improve the model.

Step 7: Successful Model

If performance is good:

• The model becomes a Successful Model
• It can be deployed in real-world applications.

 ******************** >< ********************