Become an AI engineer

# How models work, plainly

How models work, plainly is a unit of 29 lessons in Rabbithole's Become an AI engineer course, at levels 1 to 2.

## Lessons

1. Machine learning: computers that learn from data · Level 1
2. Neural network · Level 1
3. Deep learning, in plain words · Level 1
4. Embeddings: turning words into numbers · Level 1
5. Embeddings: giving words a place on a map · Level 2
6. Machine translation: from helper to translator · Level 2
7. When a model only memorises · Level 2
8. Supervised learning: learning from labeled examples · Level 2
9. Unsupervised learning: learning without labels · Level 2
10. Activation functions: the bend that lets networks learn · Level 2
11. Chat templates: the layout a model expects · Level 2
12. Gradient descent: learning in small steps · Level 2
13. Reading Learning Curves · Level 2
14. Model Explainability: Why Did the Model Say That? · Level 2
15. Object Detection: Finding and Boxing Every Object · Level 2
16. Reinforcement learning: learning by reward · Level 2
17. Softmax: from raw scores to chances · Level 2
18. Autoencoder: squeeze it, then rebuild it · Level 2
19. Backpropagation: how a network finds what to change · Level 2
20. GANs: two AIs in a contest · Level 2
21. Hyperparameters and the learning rate · Level 2
22. Meta-Learning: Learning to Learn · Level 2
23. Policy gradient: learning the rule itself · Level 2
24. Prediction-Based Exploration · Level 2
25. Recurrent neural networks: AI that reads one piece at a time · Level 2
26. Regularisation: keeping a model from memorising · Level 2
27. Residual connections: the shortcut around each step · Level 2
28. Q-Learning: A Table of Action Scores · Level 2
29. Deep Q-Learning: Swapping the Table for a Network · Level 2

## Sources

These lessons draw on 25 sources. The most used:

- [Lil'Log](https://lilianweng.github.io/)
- [MIT 6.S191: Introduction to Deep Learning](https://www.youtube.com/playlist?list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI)
- [Stanford CS224N: Natural Language Processing with Deep Learning, Spring 2024](https://www.youtube.com/playlist?list=PLoROMvodv4rOaMFbaqxPDoLWjDaRAdP9D)
- [MIT 6.S191: Introduction to Deep Learning (2026)](https://www.youtube.com/playlist?list=PLkkuNyzb8LmxFutYuPA7B4oiMn6cjD6Rs)
- [Machine Learning Crash Course](https://developers.google.com/machine-learning/crash-course)
- [Hugging Face LLM Course](https://github.com/huggingface/course)
- [Deep Learning](https://www.deeplearningbook.org/)
- [Hugging Face Deep RL Course](https://github.com/huggingface/deep-rl-class)

[All units in Become an AI engineer](https://rabbithole.pro/courses/ai-engineer)

Source page: https://rabbithole.pro/courses/ai-engineer/how-models-work-plainly