Sometimes when I write reports, I end up summarizing backpropagation, which spurs me to derive it again for myself. Backpropagation isn’t particularly complicated mathematically, but if you’re not super comfortable applying the chain rule until your arm falls off, or combining calculus and linear algebra, it might feel a bit involved. Especially when my calculus is rusty, I occasionally go down some less sensible routes and take a while to get there – hopefully, writing this down will prevent me going the wrong way again. This is something of a crash-course in the derivation, without any of the diagrams or other niceties necessary to make it even slightly intelligible.
How are we all doing today?
The final project for a module on Geographic Information Systems was, in its entirety, “essay on maps.” They expected the class to go away, do some data analysis, and write a report on the correlation between Pret a Mangers per cubic meter and average suburban decadence, or some nonsense. But that’s not what they asked for…
This guide was originally written for people taking the CS324 Computer Graphics course wishing to compile the Linux OpenGL lab code or their own coursework on a Windows machine. However, you may find it useful if you’re trying to build cross-platform OpenGL apps with C++ on Windows. The original PDF is available here, but this web version is easier to follow and features a few minor corrections and readability enhancements.