Machine Learning Basics

Understand how machines learn from data, the different types of machine learning, and how to get started building ML models.

Overview of Machine Learning

Machine Learning allows computers to learn from data and improve their performance over time. Instead of writing detailed instructions for every possible situation, developers train models using large amounts of data.

The model studies this data and identifies patterns. Once trained, it can apply these patterns to new information and make predictions or decisions.

For instance, consider an email filtering system. The system is trained using examples of spam emails and legitimate emails. Over time, it learns to recognize the characteristics of spam messages and can automatically filter them in the future.

Machine Learning Basic Process

Machine Learning systems usually follow a basic process.

First, data is collected. This data can include text, numbers, images, or audio.

Second, the data is used to train a model. During this stage, the model learns patterns from the dataset.

Third, the trained model is tested and used to make predictions or automate tasks.

Machine Learning is widely used for recommendation systems, fraud detection, language translation, image recognition, and many other applications.

What is Machine Learning?

Machine learning (ML) is a subset of AI that focuses on building systems that learn from data. Instead of being explicitly programmed, ML algorithms identify patterns and make decisions with minimal human intervention.

Types of Machine Learning

Supervised Learning

The algorithm learns from labeled training data — input-output pairs.

• Classification — Predicting categories (spam vs. not spam)
• Regression — Predicting continuous values (house prices)

# Supervised learning: Linear Regression
from sklearn.linear_model import LinearRegression
import numpy as np

X_train = np.array([[800], [1200], [1600], [2000]])
y_train = np.array([200000, 300000, 400000, 500000])

model = LinearRegression()
model.fit(X_train, y_train)
prediction = model.predict([[1500]])
print(f"Predicted price: {prediction[0]:,.0f}")

Unsupervised Learning

• Clustering — Grouping similar data (customer segmentation)
• Dimensionality Reduction — Simplifying data (PCA)
• Anomaly Detection — Finding unusual patterns (fraud)

Reinforcement Learning

Agent learns by interacting with an environment and receiving rewards. Used in robotics, game playing (AlphaGo), and autonomous systems.

ML Workflow

1. Data Collection
2. Data Preprocessing
3. Feature Engineering
4. Model Selection
5. Training
6. Evaluation
7. Deployment

Popular Algorithms

• Linear & Logistic Regression
• Decision Trees & Random Forests
• Support Vector Machines
• Neural Networks
• Gradient Boosting (XGBoost, LightGBM)