Resource Focus
Core mechanics
Revisit perceptrons, architectures, forward propagation, activations and loss functions.
Learning mathematics
Use gradient-descent and backpropagation chapters as the core computational reference.
Training discipline
Return to optimisation, initialisation, regularisation, reproducibility and debugging guidance.
Implementation
Bridge the mathematics into PyTorch with official module, autograd, optimiser and tutorial documentation.
Chapter Resource Map
Every chapter in this Module already contains its own Key Terms and References & Further Reading collections. These links open the relevant chapter and automatically expand the requested resource section.
Neurons, Architecture & Forward Computation
Chapter 1 — From Biological Inspiration to Artificial Neurons
Use the chapter resource layer to revise terminology or open the source list used for deeper verification and study.
Chapter 2 — The Perceptron
Use the chapter resource layer to revise terminology or open the source list used for deeper verification and study.
Chapter 3 — Neural Network Architecture
Use the chapter resource layer to revise terminology or open the source list used for deeper verification and study.
Chapter 4 — Forward Propagation
Use the chapter resource layer to revise terminology or open the source list used for deeper verification and study.
Chapter 5 — Activation Functions
Use the chapter resource layer to revise terminology or open the source list used for deeper verification and study.
Chapter 6 — Loss Functions
Use the chapter resource layer to revise terminology or open the source list used for deeper verification and study.
Learning, Gradients & Optimisation
Chapter 7 — Gradient Descent
Use the chapter resource layer to revise terminology or open the source list used for deeper verification and study.
Chapter 8 — Backpropagation
Use the chapter resource layer to revise terminology or open the source list used for deeper verification and study.
Chapter 9 — Optimisation and Parameter Initialisation
Use the chapter resource layer to revise terminology or open the source list used for deeper verification and study.
Generalisation, Debugging & Building
Chapter 10 — Regularisation and Generalisation
Use the chapter resource layer to revise terminology or open the source list used for deeper verification and study.
Chapter 11 — Training, Debugging and Evaluating Neural Networks
Use the chapter resource layer to revise terminology or open the source list used for deeper verification and study.
Chapter 12 — Building a Neural Network
Use the chapter resource layer to revise terminology or open the source list used for deeper verification and study.
Curated External Reference Shelf
This shelf surfaces a small set of high-value references already used by the Module. The complete chapter-specific source lists remain inside the individual chapters.
| Resource | Why it is useful | Used in |
|---|---|---|
| PyTorch Documentation | Primary framework reference across the module | Chapters 1–12 |
| PyTorch — torch.nn | Layers, activations, losses and neural-network building blocks | Chapters 1, 3, 5, 6, 10 |
| PyTorch — Automatic Differentiation | Autograd and gradient computation | Chapters 1, 4, 8 |
| PyTorch — Autograd Mechanics | Detailed automatic-differentiation behaviour | Chapters 1–12 |
| PyTorch — torch.optim | Optimisers and parameter updates | Chapter 9 |
| PyTorch — torch.nn.init | Parameter-initialisation reference | Chapter 9 |
| PyTorch — Reproducibility Notes | Determinism and reproducibility considerations | Chapter 11 |
| Deep Learning — online book | Feedforward networks, regularisation and optimisation theory | Chapters 1–12 |
Continue the Learning Journey
Return to Neural Networks
Continue the full 12-Chapter learning sequence rather than using the resource directory as a substitute for the lessons.
Open the Module →Next: Deep Learning
Continue into the next logical learning area when you are ready.
Continue Learning →NIYAMA-VIDYĀ Resources
Return to the permanent site-wide directory for Learn, Explore, Applied AI and transparency resources.
Back to Resources →Reference Transparency
External documentation and publications remain the property of their respective owners and are provided for attribution, verification and further learning. See Third-Party Rights & Attribution and the Website Disclaimer for the site-wide transparency framework.