Course Curriculum
5 chapters are available now.
Building a Backpropagation Engine
Understanding Backpropagation
Explains why backpropagation is necessary and how it works conceptually before any implementation.
Implementing Backpropagation
Walks through building a minimal autograd engine from scratch, implementing the core backward pass logic that enables automatic differentiation.
Coming Soon
Testing Backpropagation
Validates the autograd engine by running it against known gradient computations, then uses it to train a small neural network end-to-end.
Coming Soon
Conclusion
Appendix A: Topological Sort
Explains the topological sort algorithm and why it is essential for ordering nodes correctly during the backward pass through a computation graph.
Coming Soon
Credits
A comprehensive list of credits for the sources that inspired and informed the course material. Useful for further reading.