Scribd
Upload
5 views2 pages

02 Machine Learning Explained

Machine Learning (ML) is a branch of AI that allows systems to learn from data without explicit programming, identifying patterns to make predictions. There are three main types of ML: supervised, unsupervised, and reinforcement learning, each with distinct applications. The ML pipeline consists of data collection, preprocessing, model selection, training, evaluation, and deployment, utilizing various algorithms like Linear Regression and Neural Networks.

Uploaded by

Selva Kannan Subramanian
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
5 views2 pages

02 Machine Learning Explained

Machine Learning (ML) is a branch of AI that allows systems to learn from data without explicit programming, identifying patterns to make predictions. There are three main types of ML: supervised, unsupervised, and reinforcement learning, each with distinct applications. The ML pipeline consists of data collection, preprocessing, model selection, training, evaluation, and deployment, utilizing various algorithms like Linear Regression and Neural Networks.

Uploaded by

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

Machine Learning Explained

How Machines Learn from Data

What is Machine Learning?


Machine Learning (ML) is a subset of AI that enables systems to automatically learn and
improve from experience without being explicitly programmed. Instead of following
hard-coded rules, ML models identify patterns in data and use those patterns to make
predictions or decisions.

The Three Types of Machine Learning


• Supervised Learning: The model is trained on labelled data — input-output pairs.
Examples include email spam detection, image classification, and house price
prediction.

• Unsupervised Learning: The model finds hidden patterns in unlabelled data.


Examples include customer segmentation and anomaly detection.

• Reinforcement Learning: The model learns by interacting with an environment and


receiving rewards or penalties. This is how AI game-playing agents like AlphaGo were
developed.

The Machine Learning Pipeline


1. Data Collection — Gather relevant, high-quality data.

2. Data Preprocessing — Clean, normalise, and prepare the data.

3. Model Selection — Choose the appropriate algorithm.

4. Training — Feed the data to the model so it can learn.

5. Evaluation — Test performance on unseen data.

6. Deployment — Integrate the model into a real-world application.

Common ML Algorithms
Popular algorithms include Linear Regression, Decision Trees, Random Forests, Support
Vector Machines (SVM), K-Nearest Neighbours (KNN), and Neural Networks. Each has
strengths suited to different problem types and dataset sizes.

Document 2 of 5 — AI Knowledge Series

You might also like