PyTorch
Tensors, autograd and neural networks in Python.
PyTorch is taught here in 3 lessons, running from Tensors and autograd through to Modules, data and saving. Each lesson takes one topic, shows the working code, and links onward to the next, so the course can be read straight through in order.
| Track | AI & Intelligent Development |
| Lessons | 3 |
| Level | Beginner |
| Reading time | about 39 minutes |
| Prerequisites | Helpful, but not required: TensorFlow |
Lessons
- Tensors and autogradThe core data structure, moving work to the GPU, and the automatic differentiation that makes training possible.
- The training loopA complete, correct training and evaluation loop — loss, optimiser, batching, and validation that you can trust.
- Modules, data and savingWriting models as nn.Module, feeding data with Dataset/DataLoader, and persisting weights correctly.
More in AI & Intelligent Development
AI Basics AI Agents Math for AI Machine Learning scikit-learn TensorFlow Natural Language Processing LangChain Ollama OpenCV Codex Claude Code OpenCode Vibe Coding Selenium Playwright
FAQ
How long does the PyTorch course take?
It has 3 lessons, about 39 minutes of reading. Expect roughly twice that if you type out and run every example.
Do I need prior experience for PyTorch?
Not strictly. It helps to have read TensorFlow first, because some lessons build on it, but every lesson explains its own assumptions.
What should I read after PyTorch?
Continue with Natural Language Processing (3 lessons), the next course in AI & Intelligent Development.
Last refreshed 2026-09-18.