AI Hints
Subscribe
Home›Deep Learning Tutorial
Free course

Deep Learning Tutorial

Learn deep learning from tensors to building your own GPT, step by step, in simple words. Every idea is shown with animations, real PyTorch code and real training runs.

📚 92 lessons▶ 3:07:26+ of video💻 112 code examples🖼 103 screenshots
Start learning now ❯Watch the full video
The complete Deep Learning course, free on YouTubeWatch on YouTube ↗

What you will learn

  • Tensors, autograd, and the training loop in PyTorch
  • Neurons, activations, backpropagation and optimisers
  • CNNs, ResNet and data augmentation
  • RNNs, LSTMs, attention and transformers
  • Building and training your own GPT
  • Autoencoders, GANs and diffusion models
  • Debugging, tuning, shrinking and serving models
  • A capstone project, quizzes and interview preparation

Course contents

Every lesson has its own page with the explanation, code you can copy, the real output, screenshots from the video, and a link that jumps straight to that moment in the video.

2. Tensors and Autograd

  1. Tensors7:46
  2. GPUs10:03
  3. Autograd11:48

3. Your First Real Networks

  1. Building with nn.Module14:06
  2. Datasets and Batches15:57
  3. The Training Loop17:42

5. Optimisers and Learning Rates

  1. Optimisers29:32
  2. The Learning Rate31:10
  3. Weight Initialisation33:09

8. Famous Architectures

  1. Famous Architectures47:44
  2. ResNet49:21
  3. Data Augmentation51:27

9. Sequences and Memory

  1. Sequences and Memory53:41
  2. Tokens and Embeddings55:29
  3. LSTM and GRU57:38

10. Attention

  1. Attention1:00:10
  2. Query, Key, and Value1:02:00
  3. Multi-Head Attention1:03:58

11. Transformers

  1. Positions Matter1:05:45
  2. The Transformer Block1:06:50
  3. Building a GPT1:09:10

12. Training Your GPT

  1. Training Your GPT1:10:48
  2. From Tiny to Giant1:13:15

13. Autoencoders and VAEs

  1. Autoencoders1:14:55
  2. Denoising1:16:46
  3. Variational Autoencoders1:17:58

14. GANs and Diffusion

  1. GANs1:19:42
  2. Diffusion Models1:21:54

15. Transfer Learning and Debugging

  1. Transfer Learning1:24:27
  2. Fine-Tuning1:26:40
  3. Debugging Neural Networks1:28:15

16. Faster, Smaller, Shipped

  1. Training Faster1:30:53
  2. Smaller and Faster Models1:33:02
  3. Serving a Network1:34:56

18. How Language Models Really Work

  1. Real Tokenisers1:42:56
  2. Choosing the Next Token1:44:46
  3. Why Chatbots Are Fast1:46:26

19. Using Pretrained Transformers

  1. Using Pretrained Transformers1:47:50
  2. Fine-Tuning a Transformer1:49:24

20. Detection and Segmentation

  1. Object Detection1:51:12
  2. Segmentation1:53:09

21. Text to Image, and Rewards

  1. Text to Image1:54:56
  2. Deep Reinforcement Learning1:57:09

22. Inside the Black Box

  1. Seeing Inside the Black Box1:59:25
  2. Adversarial Examples2:01:14

23. Training at Scale

  1. Training at Scale2:02:59
  2. Finding the Bottleneck2:04:32
  3. Experiments and Tests2:05:56

25. Layers Up Close

  1. Inside Batch Norm2:12:22
  2. Inside Dropout2:14:03
  3. Label Smoothing2:15:39

26. Tuning with Discipline

  1. The Learning Rate Finder2:17:10
  2. Smarter Hyperparameter Search2:18:18
  3. Logging Every Run2:19:55

27. Making Models Small

  1. Pruning2:21:26
  2. Quantisation2:23:09
  3. Knowledge Distillation2:24:37
  4. Mixed Precision2:26:05

30. Myths and Hard Questions

  1. Deep Learning Myths2:42:40
  2. Hard Deep Learning Questions2:45:25

31. Capstone and Review

  1. Capstone: Finishing Aria2:49:58