Dataflow matrix machines (by Anhinga anhinga)

I updated my Mastodon for the first time since I created it in November: dmm.dreamwidth.org/65045.html

It turns out I follow this cool account: arXiv Highlights AI/ML sigmoid.social/@arxiv@creative.ai

Twitter seems to gradually becoming somewhat less effective as a source of information; I should probably read Mastodon more...

This week, Nov 17-18, Thu-Fri, 8am-11:45am Boston time, "Quantum physics and the first-person perspective": www.essentiafoundation.org/quantum-physics-and-the-first-person-perspective/seeing/

JuliaCon 2023, juliacon.org/2023/ the call for proposals is posted, deadline Dec 18: pretalx.com/juliacon2023/cfp


I've spent more quality time focusing of two breakthroughs in understanding the nature and the behavior of machine learning models which came from the "penumbra" of "prosaic alignment" start-ups and which I wrote about in my previous two posts.

"Grokking is (more or less) solved." I took brief notes between Oct 21 and Oct 23: github.com/anhinga/2022-notes/tree/main/Grokking-is-solved

"Generative autoregressive models are similators." I took extensive notes between Oct 5 and Oct 23: github.com/anhinga/2022-notes/tree/main/Generative-autoregressive-models-are-similators

I am continuing to develop thoughts related to these topics, I am going to gradually write more about those topics in the comments.

kidger.site/thoughts/jax-vs-julia/

Various correspondencies between JAX and Julia constructions he is listing there are quite useful for people practicing either JAX or Julia.

(I am having good time with both JAX and Julia this year.)

Chris Rackauckas says: "In 2022, the difference between symbolic computing and compiler optimizations will be erased in Julia. Anyone who can come up with a set of symbolic mathematical rules will automatically receive an optimized compiler pass to build better code."

Details in the comments.

73 million developer accounts, 100 million repositories, and plenty of processes depending on GitHub being up...

I created this rather interesting color thing a few days ago and committed it and the Julia notebook which generated it



and now I continued this line of thinking and made another one (and a much cleaner version of code)




and hoped to commit it as well, but...

UPDATE: GitHub is fixed: github.com/anhinga/late-2021-julia-drafts/tree/main/color-motifs

- JuliaCon 2021 (July 30)

- ML Collective Research Jam #3 (Aug 4)

- ML Collective Research Jam #4 (Sep 22)

- Stuttgart Julia Programming Language Meetup (Oct 23)

juliacon.org/2021/ and live.juliacon.org/

The talk schedule: pretalx.com/juliacon2021/schedule/ (the default is UTC time, I see that I can switch to New York)

If you register (free), this gives access to discord, gathertown, and hackaton.

I'll keep notes in the comments.

This sounds very close to some of the things I was playing with recently (differentiable image warps with interpolations and such), but probably done in a more professional manner (for example, resulting in pull requests to a library everyone uses, making a *.jl repository, etc.):

somtambe.github.io/blogs/jsoc_blog_2/

Remarkably enough, I learned about this from someone liking it in LinkedIn and thus placing it to my LinkedIn feed. I guess I was successful in convincing LinkedIn that my interests are centered around Julia.