AI: Machine Learning & Model Training
Neural networks: zero to hero | Sri AI
Advanced
1 views
Course overview
From a single neuron and hand-written backpropagation all the way to building a GPT, one video and notebook at a time.
Level: Advanced · Mode: Part-time
Who this course is for
Engineers who want deep intuition, not just working code.
What you will learn
- Implement backpropagation by hand
- Build language models step by step
- Diagnose training with activations and gradients
- Build a small GPT
Syllabus
- Module 1: Micrograd and backprop
- Module 2: Bigram models
- Module 3: MLPs
- Module 4: Batch normalisation
- Module 5: WaveNet
- Module 6: Building GPT
- Module 7: Tokenisers
Final project
Every module ends in hands-on practice, and the course ends with a project you build and present. Your certificate names that project.
Before you start
PyTorch from zero.
Open-source tools you will use
Based on Andrej Karpathy's open Zero to Hero series (MIT).