Session 1: A Practical Introduction to Machine Learning with Python

Learning objectives

• Explain the difference between artificial intelligence, machine learning, and deep learning.

• Frame the problem as “Data → Feature → Model → Evaluation → Deployment”.

• Build and evaluate a simple classification model with a real-world example.

Prerequisites

• Basic familiarity with Python and basic statistical concepts (mean, variance, precision, precision-recall).

• Install Python 3.10+, libraries: numpy, pandas, scikit-learn, matplotlib.

Meeting Roadmap (90 minutes)

1. Fundamental Concepts (15 minutes)

2. Data and Feature Engineering (15 minutes)

3. Building a Classification Model (30 minutes)

4. Evaluation and Improvement (20 minutes)

5. Exercise and homework (10 minutes)

1) Basic concepts (summary)

• AI: Any method that produces intelligent, human-like behavior.

• ML: A subset of AI that learns from pattern data (without explicit programming of rules).

• DL: A subset of ML based on deep neural networks.

• Main types of ML: supervised (classification/regression), unsupervised (clustering/dimensionality reduction), reinforcement.

2) Sample problem: Spam detection of short messages

We want to classify text like “You’ve won! Click the link…” into two spam/ham labels.