Deep Learning Foundations with PyTorch
Tensors, autograd, training loops and the core architectures — build MLPs and CNNs from scratch, then with PyTorch.
🎯 Who it's for
You know classical ML and want the deep-learning base that the LLM, computer-vision and NLP tracks build on.
✅ Prerequisites
- Introduction to Machine Learning or equivalent
- Python fluency
- Solid gradient-descent intuition
- A GPU — we provide one in the browser lab
Topics covered
- Tensors and automatic differentiation
- Training loops, optimisers and schedulers
- MLPs and backpropagation from scratch
- CNNs and transfer learning
- Regularisation and debugging training
- A first look at attention
Expected completion timeline
9 weeks part-time at 8–12 hours per week ≈ 2.1 months. Self-paced learners can go faster; the live cohort keeps this pace.
Autograd and training loops
You produce: An MLP trained from scratch, then re-implemented cleanly in PyTorch.
CNNs and transfer learning
You produce: An image classifier fine-tuned on a custom dataset.
Debugging, regularisation and project
You produce: A documented model and training report.
🧭 Where this fits
Gateway to the LLM / Generative-AI Engineer and CV / NLP Engineer paths. See the career & salary map for the full path, the expected pay by region, and the total cost.
💳 Delivery & fees
Available in all four delivery formats. Fees vary by format and are confirmed on your advisor call; instalments available.
Add this to your plan
Book a call and we'll place this course in a full path toward the role you want.
Talk to an advisor