Unlocks after Module 4The AI Engineering Program
Module 5: Deep Learning & Transformers from Scratch
Train neural networks in PyTorch and build a working mini-GPT, so LLMs stop being a black box.
28guided hours
10lessons
5 of 13in the program
Lessons
10 lessons, in order. Each one unlocks when you finish the one before it.
- 5.1PyTorch tensors and autograd
- 5.2The training loop: batches, loss, optimiser, GPU in Colab
- 5.3Multilayer networks, overfitting and regularisation
- 5.4Convolutional networks and transfer learning
- 5.5Tokenisation and embeddings
- 5.6Attention, built by hand
- 5.7The transformer block
- 5.8Build and train a mini-GPT on Indian-language text
- 5.9Pretrained models from the Hugging Face Hub: pipelines and sentence embeddings
- 5.10Module project
Your first lesson is on us.
AI vs ML vs DL vs GenAI: deep notes, a hands-on lab and a quiz. No card. No catch.