# Intro to Deep Learning

Source: https://freeaicourses.com/courses/kaggle-intro-to-deep-learning
Last checked: 2026-09-15

## Who it is for

- People who finished Intro to Machine Learning
- Anyone who wants to try deep learning before committing

## Who should skip it

- Anyone who wants PyTorch
- People who want the theory behind backpropagation

## What you can do afterwards

- Build and train a small neural network
- Recognise overfitting and underfitting
- Know what dropout and batch normalisation are for

## What the course covers

- A single neuron: What a unit in a network actually computes.
- Deep networks and training: Stacking layers and fitting them with gradient descent.
- Overfitting and regularisation: Keeping a model from memorising the training data.

## What works

- Quick to finish
- Free GPU notebooks
- Clear exercises

## What does not

- Uses Keras, while most research uses PyTorch
- Shallow by design

## Take after

- Practical Deep Learning for Coders
- Neural Networks: Zero to Hero

## Verdict

A good taster once you've done Kaggle's Intro to ML. It won't make you a deep learning engineer, but you'll train a real network in an afternoon and know whether you want more.

## Related pages

- [Practical Deep Learning for Coders](https://freeaicourses.com/courses/practical-deep-learning-for-coders)
- [Neural Networks: Zero to Hero](https://freeaicourses.com/courses/neural-networks-zero-to-hero)
- [Kaggle Learn](https://freeaicourses.com/platforms/kaggle)
- [All free AI courses, rated](https://freeaicourses.com/courses)