Posts about main (old posts, page 3)


Deep learning VS mbed linux?

Been messing with some arm SBC for a couple days, trying to build a mainline kernel and uboot for it -- unsucessfully. What I've noticed however, is that I'm really curious about the stuff. I hadn't been into it for a year or two I think, and now after the pause... I feel curious.

Some cool and motivating talks:


I really still feel like coding is a detestable and shameful activity, but it seems I really miss it. Should I forget about geometry and sltheory for a while? Perhaps even try non-ML GSoC?

Some more vids:

Betancourt: higher-order autodiff

Just stumbled upon an open tab with Betancourt's "Geometric theory of higher order automatic differentiation" which I started reading the new year night but quickly got distracted from. I remember my first feeling was that it's slightly more verbose than actually needed and that I'd have used some different wordings. While this might be true, I'm finding the survey in its intro very clear and explaining. I must remind my imaginary interlocutor that I have not as of yet went through any course of differential geometry, only skimmed some textbooks and wikis. I've been really struggling. Mainly because of terrible notation and language established by physicists, I believe, and employed in most classic texts. There are exceptions of course. Some of seemingly good texts include e.g. works of Lee. I think I would've solved my problems if I read carefully Lee's monographs and walked through exercises therein. I'm not yet ready to make this effort (not ready to do anything at all).

As for higher-order differential geometric structures, I have only encountered jets when reading Arnold's "lectures on PDEs", where they were in fact treated (if my memory doesn't deceive me) as "things" that appear in Taylor expansions, without actually specifying their "datatypes".

Now, here's what I actually wanted to remember when I started typing this note: a good survey rapidly introducing principal concepts before verbose and detailed body of a text makes a lot of difference. Lee, say, pours on you quite an amount of information that makes use of terms that haven't been yet made concrete. And that information might give you a good intuition if you already got some very basic framework of concepts and notations to add new nodes and connections to. Betancourt on the other hand throws "pullbacks" and "pushforwards" at you in the very beginning. He throws them pretty concretized, almost tangible, in the sense that he defines domains and ranges of the mappings, and essential properties of their actions. He doesn't spend too much time on it, doesn't overload the reader with questions like existence. These questions are important later for rigorous analysis, but not for sketching the initial map of the field, not for initial understanding of connections to other concepts.

Brain is a terribly lazy thing. At least mine is. The art of writing (when the purpose of writing is to explain a subject and convey a message) is in hacking reader's brain so as to leave it no chance to object comprehending the message. That's an obvious thing that I always knew too. Yet I tend to forget this when actually writing.