Module 14: Modern ML and Your Learning Roadmap

This is the final module, and it looks outward rather than inward. First you will meet the algorithms that dominate practice but sit just beyond this course: gradient boosting, which wins most tabular competitions, and neural networks, which underpin everything from image recognition to large language models. Then you will step back and map the whole landscape — what to learn next, in what order, and why, depending on where you want to go.

The goal is not to make you an expert in these methods in one week. It is to leave you with an accurate mental map of the field, so that when you encounter these terms in a job posting or a meeting, you know what they mean, when they apply, and where to go to learn more.

Learning Objectives

By the end of this module, you will:

  • Explain gradient boosting and how sequential ensembles differ from a random forest’s parallel ones
  • Describe neural network fundamentals — layers, neurons, activation functions, and backpropagation
  • Map the algorithm landscape from linear models and ensembles through CNNs, RNNs, and Transformers
  • Evaluate the interpretability–performance spectrum and choose methods that fit your constraints
  • Judge when advanced methods beat classical ML based on data type, dataset size, and requirements
  • Explain foundation models and how transfer learning reshaped the modern ML workflow
  • Identify the areas worth studying next and the learning pathway that fits your career goals
  • Recognize the skills beyond modeling — engineering, communication, deployment — that practitioners rely on

Module Resources

Lecture

Resource Link
📊 Week 14 Slides View slides

Chapters & Notebooks

Chapter Topic Colab Notebook
33 Beyond the Basics: Modern ML Algorithms Open in Colab
34 The Machine Learning Roadmap: Where to Go Next —

Lab

There is no separate lab this week. Use the Thursday session to finish your final project and to work through the roadmap in Chapter 34 — the resources there are the most useful thing you can take with you from this course.

Reference

Resource Link
📋 Module 14 Cheat Sheet View cheat sheet