Learn to use AI

# How a network learns

How a network learns is a unit of 8 lessons in Rabbithole's Learn to use AI course, at level 2.

## Lessons

1. Activation functions: the bend that lets networks learn · Level 2
2. Gradient descent: learning in small steps · Level 2
3. Backpropagation: how a network finds what to change · Level 2
4. Softmax: from raw scores to chances · Level 2
5. Residual connections: the shortcut around each step · Level 2
6. Hyperparameters and the learning rate · Level 2
7. Regularisation: keeping a model from memorising · Level 2
8. Reading Learning Curves · Level 2

## Sources

These lessons draw on 15 sources. The most used:

- [Stanford CS224N: Natural Language Processing with Deep Learning, Spring 2024](https://www.youtube.com/playlist?list=PLoROMvodv4rOaMFbaqxPDoLWjDaRAdP9D)
- [Machine Learning Crash Course](https://developers.google.com/machine-learning/crash-course)
- [MIT 6.S191: Introduction to Deep Learning](https://www.youtube.com/playlist?list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI)
- [MIT 6.S191: Introduction to Deep Learning (2026)](https://www.youtube.com/playlist?list=PLkkuNyzb8LmxFutYuPA7B4oiMn6cjD6Rs)
- [Hugging Face LLM Course](https://github.com/huggingface/course)
- [Neural Networks: Zero to Hero](https://www.youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://arxiv.org/abs/1502.03167)
- [Deep Learning](https://www.deeplearningbook.org/)

[All units in Learn to use AI](https://rabbithole.pro/courses/learn-ai)

Source page: https://rabbithole.pro/courses/learn-ai/how-a-network-learns