The fundamental strategy of calculus is to replace a nonlinear function with a tangent line approximation to that function. This greatly simplifies calculations, and the approximation is often accurate enough to be useful.
Do you think Tesla could have made it through production hell without Musk? Nobody knows the technical details of Tesla the way Musk does. Nobody would sleep in the factory like Musk does. Who else would have shipped a production line from Europe by air? The dude solves problems and puts out fires and keeps Tesla on the right path like nobody else. People like Elon Musk are not fungible.
The general consensus is that Tesla experienced production hell solely because of Musk. Moreover, their impending cash crunch is also due to Musk rushing through things rather than stepping back for a minute to spend quality time figuring out the details.
People like Musk aren't just replaceable, they should be replaced so soon as possible to lookout the damage they do.
The NAND to Tetris textbook is a masterpiece. (The book is called The Elements of Computing Systems: Building a Modern Computer from First Principles. The authors are Nisan and Schocken).
I worked through the entire textbook by myself, doing all the projects, and having no previous knowledge of computer architecture or compilers. It was a challenging but smooth process. The difficulty level was just right and I didn't get frustrated.
The computer you build is designed brilliantly. It's as simple as it can be, while still being a real computer can be that can play video games.
I think Hinton himself was there in the 80s pioneering neural networks, and he stuck with it this whole time. He was one of the first researchers to demonstrate the use of backpropagation to train neural networks.
