fast_574r7{note, "1/7"}

when people talk

they give the impression you need years of study to learn all this:

1. linear algebra
2. and then set theory
3. and then calculus
4. real analysis
5. ...

there's a lot of gatekeeping out there that says like "oh if you're going to be a real deep learning practitioner you have to finish, you know, a graduate level course in linear algebra"...
you don't !!
but here's the truth, the actual linear algebra you need almost all the time to do, in basically all DL, is matrix multiplication !!

DL uses fancy jargon to sound intimidating

underlying concepts are simple, not as complex as they seem — simple as replacing negatives with zeros (ReLU "rectified linear unit").

the reality is that for academics to get their papers published, they need to make them sound as impressive and sophisticated as possible.
one of the ways that they do that is to introduce jargon.
just remember, when you come across a word or phrase that you haven't seen before, it will almost certainly turn out to be referring to a very simple concept.

being not that good at coding yet, it's actually an opportunity 'cause you have a really fun project to learn to code in.
so, a lot of people have become good coders by doing the fast.ai course, 'cause as you do the course, you'll learn about a lot of computer science concepts

1. object-oriented programming
2. functional programming
3. mapping over a list
4. list comprehensions
5. GPU acceleration...
6. ...

this is an opportunity, it's not a problem.

foundational concepts, core principles remain the same

(e.g., CNNs since 1996), the basic ideas are forever, the more you learn about those basic ideas, the more you'll recognize those tweaks as simple little tricks that you'll be able to quickly get your head around.

occasionally explore other areas for diversity.

after 3 months, you'll be amazed at how much you understand things you had no idea about before.