Modern AI Engineering

Module 2 · Foundations

Learning from Data

In this module, we will learn what Machine Learning is, the different ways a machine can learn, and the basic terms we will keep using in every later module of this AI Engineering Course.

By the end of this module, we will know how a model learns from data, how we measure it, and how we stop it from overfitting.

Lessons

  1. 2.1 Machine Learning from First Principles
  2. 2.2 Labeled vs Unlabeled: Two Ways Machines Learn: Supervised Learning · Unsupervised Learning · Differences Between Supervised and Unsupervised Learning
  3. 2.3 Predicting Numbers vs Categories: Regression Compared: Linear Regression · Logistic Regression · Differences Between Linear Regression and Logistic Regression
  4. 2.4 Feature Engineering: Turning Raw Data into Signal
  5. 2.5 Precision and Recall: Picking the Right Metric: The problem we are trying to solve · The four possible outcomes · What is Precision? · What is Recall? · Precision vs Recall · When to use which one? · A quick recap of the formulas · Summary
  6. 2.6 L1 vs L2 Loss: Choosing Your Error Penalty: L1 Loss Function · L2 Loss Function · How to decide between L1 and L2 Loss Function?
  7. 2.7 Regularization: Stopping Overfitting with L1 and L2: What is overfitting? · L1 Regularization or Lasso Regularization · L2 Regularization or Ridge Regularization
  8. 2.8 Reinforcement Learning: Teaching Agents Through Reward: The Big Picture · What is Reinforcement Learning? · A Simple Real-World Analogy · The Building Blocks of RL · The Reinforcement Learning Loop · Reinforcement Learning vs Supervised vs Unsupervised Learning · Episode, Return, and Discount Factor · Exploration vs Exploitation · Common Families of RL Algorithms · Where Is Reinforcement Learning Used? · Why Reinforcement Learning Is Hard · Quick Summary
  9. 2.9 Contrastive Learning: Training by Comparison: What is Contrastive Learning? · Why do we need Contrastive Learning? · The key idea behind Contrastive Learning. · Positive pairs and Negative pairs. · How does Contrastive Learning work step-by-step? · Loss functions used in Contrastive Learning. · Popular Contrastive Learning methods. · Real-world use cases of Contrastive Learning. · [Feature Engineering in Machine Learning](https://www.youtube.com/watch?v=QLlywrWuXag) (Video) · [One-hot Encoding in Machine Learning](https://www.youtube.com/watch?v=6AmedU5i9go) (Video)

← Module 1: AI Engineering Starter Kit · Module 3: Neural Architectures Deep Dive →