The main video is talking about a genetic breeding model of how to make machines learn.

This method is simpler to explain or just show.

Here's a machine learning to walk or play Mario or jump real high.

A genetic code is an older code, but it still checks out,

and I personally suspect in the future genetic models will have a resurgence as compute power approaches crazy pants.

However, the current hotness is deep learning and recursive neural networks.

And that's where the linear algebra really increases and explainability in a brief video really decreases.

But if I had to kind of explain how they work in a footnote just for the record, it's like this.

No infinite warehouse, just one student.

Teacherbot has the same test, but this time builder bot is dial adjustment bot, where

each dial is how sensitive one connection in the student bot's head is.

There's a lot of connections in its head, so a lot of dials. A lot.

Teacherbot shows student bot a photo and dial adjustment bot adjust that dials stronger or

weaker to get student bot closer to the answer. It's a bit like adjusting the dial on a radio.

Is that still a thing? Do cars have radios still? I don't know. Anyway, you might not know

the exact frequency of the station, but you can tell if you're getting closer or further away.

It's like that, but with 100,000 dials and a lot of math. And that's just for one test question.

When teacher bot introduces the next photo, dial adjustment bot needs to

adjust all the dial so that student bot can answer both questions. As the test gets longer,

this becomes an insane amount of math and fine tuning for dial adjustment bot. But when it's done,

there's a student bot who can do a pretty good job at recognizing new photos,

though still suffers from some of the problems mentioned in the main video.

...