Learn Machine Learning (ML)

This lesson also uses third party materials for studies:

1. Introduction To Machine Learning

This lesson provides a foundational understanding of Machine Learning (ML), a key subset of Artificial Intelligence (AI). You’ll explore:

• What AI & ML are – Definitions, goals, and historical context.

• How ML differs from traditional programming – Learning from data rather than explicit rules.

• Types of ML systems – Supervised, unsupervised, and reinforcement learning.

• Common ML tasks – Regression, classification, clustering, and anomaly detection.

• Key algorithms – K-Nearest Neighbors, Decision Trees, and Neural Networks.

• The rise of Deep Learning – Why it revolutionized AI with big data and advanced computing.

By the end, you’ll grasp how machines learn from data and see real-world applications of ML. Let’s dive in throught the link below! 🚀

a. introduction_to_machine_learning.ipynb – Colab

 2. Lesson 1: Introduction to Machine Learning.

This lesson serves as a hands-on, practical introduction to Machine Learning (ML), covering its core concepts, real-world applications, and how it differs from traditional programming.

Key Topics Covered:

• Why ML? – Solving complex problems where explicit rules are hard to define (e.g., language translation, image recognition).

• Types of ML:

  • Supervised Learning (predicting known targets from labeled data).

  • Generative Tasks (creating new content like text or images).

  • Self-Supervised Learning (learning from unlabeled data).

  • Reinforcement Learning (learning through rewards/punishments, e.g., game AI).

• Large Language Models (LLMs) – How models like ChatGPT are trained in stages.

• A Practical Example: Text Classification – Building a simple ML model to classify text genres (e.g., sci-fi vs. fantasy).

What to Expect:

• Theory + Code: Jupyter notebooks with exercises to implement ML concepts.

• No prior expertise needed – Explanations cater to all levels, with optional deep dives into math.

• Foundational knowledge for more advanced ML/Generative AI courses.

By the end, you’ll understand how machines learn from data and see ML applied to real-world problems. Let’s get started! 🚀.

Access the lesson here: lesson_1.ipynb – Colab

3. Lesson 2: Hands-on Linear Models

This lesson dives into practical implementation of linear models for text classification, using real-world Yelp review data. You’ll learn to preprocess text, train a model, and evaluate its performance—all while understanding the math behind the scenes.

Key Topics Covered:

• Data Preparation:

  • Loading and exploring the Yelp review dataset (ratings 1–5).

  • Converting text into numerical features using bag-of-words (CountVectorizer).

• Model Training:

  • Multiclass linear classification with logistic regression.

  • How weights and scores translate to predictions.

  • The role of softmax in converting scores to probabilities.

• Evaluation & Theory:

  • Measuring accuracy and detecting overfitting (train vs. test performance).

  • Loss functions (cross-entropy) and gradient descent for optimization.

  • Interpreting word weights to see how the model makes decisions.

What to Expect:

• Hands-on coding with scikit-learn and pandas.

• Math breakdowns (optional but insightful) on how linear models work.

• Real-world relevance: Learn to judge model quality against a baseline (e.g., a “dumb” constant classifier).

By the end, you’ll have built a working text classifier and gained intuition for tuning linear models. Ready to code? Let’s go! 🚀

Access the lesson here: lesson_2.ipynb – Colab

Further Reading:

1. Welcome To Colab – Colab
2. scikit_learn_acceleration_with_gpu.ipynb – Colab
3. Welcome: Introduction to Machine Learning Labs.ipynb – Colab
4. Welcome To Colab – Colab

Congratulations! 🚀