Learn AI From Scratch. Figure 1: Let's build the future of software. src: mistigris. Welcome. This is a draft curriculum of a bunch of topics designed as minimalist as possible so you can use a phone or tablet, since that's how I work through this material pulling out a …

We will learn the 'full stack' of modern deep learning systems by building our own library from scratch in your language of choice. Neural networks have different architectures just like there is different computer hardware architectures (x86, RISC, ARM).

We learn what a field is. If you're curious in the introduction here he shows how the rational number line has been raised on the y-axis showing how all numbers on a line through the origin (0,0) are equal on the rational strip.

We teach students to derive things in geometry, but a lot of times the exercises test if they know the theorem, not the proof. To do well in mathematics, you should learn methods and not results. And you should learn how the methods were invented.

Right now there is all kinds of physics-informed machine learning going on to numerically solve ODEs. We also will learn epidemic models and other dynamic systems should you want to work in quantitative finance or a research programmer in a medical lab.

We learn analytical databases and their internals from how s3 Amazon buckets work, how low-latency networking works, search space complexity reduction and designing microservices. We will learn about performance engineering and the basics of operating systems.

This is the first term of the Mathematical Tripos where we learn how to do university level math, here we learn basic real analysis/calculus since it's only taught in Lent but we'll need it now in Michaelmas.

If you know calculus you can skip this but it will help set us up to learn Axler's graduate analysis book next term. The best book that covers trig series to continuity to convergence is David Bressoud's A Radical Approach to Real Analysis. It teaches modern analysis as it was invented and fits well with Mechanics.