Deep learning and model adaptation

Understand neural networks and transformers, and adapt models with fine-tuning.

This is you

You want to know how models work inside, not only how to call them. You like mathematics a little, and you want to change models so that they fit your task.

Where you are going

A deep learning engineer

Explain how neural networks and transformers learn
Train a small network, and read its learning curves
Decide when fine-tuning is worth it, and when a prompt is enough
Adapt a model, and prove that it became better

3 stages
10 courses, 10 available now
About 160–212 hours of study
10 certificates of completion

How much code you need

No code
Read code
Some code
Code is central

Code is central, and so are some mathematics. The mathematics course comes first, and the lessons explain each idea with pictures before formulas.

Your route, stage by stage

Each stop is a course. Its shape tells you how much of it to take.

Full course. The whole course, with its practice. It leads to a certificate of completion.
Concepts. Only the concept modules, read without running code. They lead to a concepts certificate.
Optional. Useful for some people. You do not need it, and it is not counted in the time.

You, today
Stage 1 Foundationsabout 46–62 h
1. AI Career Foundations: Roles, Skills and Roadmaps
  Full course4–6 h
  See where model work fits in AI teams.
2. Python for Practical AI Engineering
  Full course18–24 h
  Python for every model that you train.
3. Essential Mathematics and Statistics for AI
  Full course12–16 h
  Vectors and how models learn: you need them here.
  Focus: If you already studied this, do its final assignment instead.
4. SQL and Data Preparation for AI
  Full course12–16 h
  Prepare training data.
  Focus: If you already studied this, do its final assignment instead.
Stage 2 How models learnabout 54–68 h
1. Machine Learning: From Problem to Reliable Model
  Full course26–32 h
  Machine learning first: deep learning builds on it.
  Focus: If you already studied this, do its final assignment instead.
2. Deep Learning and Transformers Explained
  Full course28–36 h
  The core of this path: neural networks and transformers.
Stage 3 Adapt modelsabout 60–82 h
1. LLMs: How They Work and How to Choose One
  Full course8–12 h
  How LLMs work, and how to choose one.
2. Building Reliable Applications with LLM APIs
  Full course22–30 h
  Use LLMs through their APIs.
3. Evaluating and Testing AI Systems
  Full course20–26 h
  Prove that an adapted model is better.
4. Fine-Tuning and Adapting AI Models
  Full course10–14 h
  Fine-tune and adapt models.
You arriveA deep learning engineer

Earn certificates as you go

You do not need to finish the whole path to show what you learned. Each full course gives a certificate of completion, and each concepts course gives a concepts certificate. Share each one when you get it.

When you are ready, prepare for the interview: Interview preparation: Machine Learning Engineer

Make it my path All learning paths

Choose this goal in your profile. My learning then shows your progress on this route, and the weeks it takes at your pace.