My "year in review"
Dec. 30th, 2019 02:41 pm![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png){kind=small}
dmmOne thing I have not written here about: I was spending more time this Fall reading various literature on mind-body problem (a prominent topic in the early years of anhinga-anhinga livejournal), and I was becoming extremely annoyed that nobody seems to be making any progress towards understanding how to deal with qualia and how to incorporate them in our models. So I came up with a modest proposal: let's assume that one can typically find a way to combine several qualia with coefficients. If we assume that, we can start moving forward:
See pages 3-4 of github.com/anhinga/2019-design-notes/blob/master/research-notes/research-notes-dec-2019.pdf for details.
Other than that, here are main "external" events of the year in my life (I only include links, if there is no post in this blog mentioning the event, otherwise I just mention the month when there was a related post in this blog).
Feb-Mar: I did an experimental study on sparsely connected neural nets, and how the structure emerges in them during training: anhinga-drafts.dreamwidth.org/29924.html
June: I learned to work with shaders, and created some Shadertoy animations.
(July-)September: My work as a software engineer in geographically-oriented software companies came to an end after 18+ years, and I fully switched to focusing only on dataflow matrix machines and related topics.
October: "Revolutionary" by Jason Priestly is now available.
November: I discovered a rather hard-core meditation book; discovered a new book by Carlo Rovelli, "The order of time".
December: I wrote a number of posts here related to neural networks and dataflow matrix machines; wrote a new "white paper" on dataflow matrix machines and an interdisciplinary collaborative research agenda; also I created anhinga.github.io and www.cs.brandeis.edu/~bukatin/dmm_next.html earlier in the year, and spent some time restructuring my resume and linkedin profile to reflect my shift away from traditional software industry and more fully towards dataflow matrix machines-related research and experimental open-source software development.
I played quite a bit with trying various parts of Python ecosystem and documenting those experiments, and with design notes for the next generation of dataflow matrix machines: github.com/anhinga/2019-python-drafts and github.com/anhinga/2019-design-notes
I played quite a bit with this new project and its "drafts" subdirectory, but it is still not quite ready for anything: github.com/anhinga/population-of-directions
I also interacted with a number of people here on dreamwidth and on livejournal (much more than in recent years, this was very interesting).
I generally shifted quite a bit towards dreamwidth and this blog during this year, and away from livejournal; this was not planned, but just happened "organically".
I hope for us all to have a creative New Year, while avoiding disasters which seem to be lurking behind every corner these days...
See pages 3-4 of github.com/anhinga/2019-design-notes/blob/master/research-notes/research-notes-dec-2019.pdf for details.
Other than that, here are main "external" events of the year in my life (I only include links, if there is no post in this blog mentioning the event, otherwise I just mention the month when there was a related post in this blog).
Feb-Mar: I did an experimental study on sparsely connected neural nets, and how the structure emerges in them during training: anhinga-drafts.dreamwidth.org/29924.html
June: I learned to work with shaders, and created some Shadertoy animations.
(July-)September: My work as a software engineer in geographically-oriented software companies came to an end after 18+ years, and I fully switched to focusing only on dataflow matrix machines and related topics.
October: "Revolutionary" by Jason Priestly is now available.
November: I discovered a rather hard-core meditation book; discovered a new book by Carlo Rovelli, "The order of time".
December: I wrote a number of posts here related to neural networks and dataflow matrix machines; wrote a new "white paper" on dataflow matrix machines and an interdisciplinary collaborative research agenda; also I created anhinga.github.io and www.cs.brandeis.edu/~bukatin/dmm_next.html earlier in the year, and spent some time restructuring my resume and linkedin profile to reflect my shift away from traditional software industry and more fully towards dataflow matrix machines-related research and experimental open-source software development.
I played quite a bit with trying various parts of Python ecosystem and documenting those experiments, and with design notes for the next generation of dataflow matrix machines: github.com/anhinga/2019-python-drafts and github.com/anhinga/2019-design-notes
I played quite a bit with this new project and its "drafts" subdirectory, but it is still not quite ready for anything: github.com/anhinga/population-of-directions
I also interacted with a number of people here on dreamwidth and on livejournal (much more than in recent years, this was very interesting).
I generally shifted quite a bit towards dreamwidth and this blog during this year, and away from livejournal; this was not planned, but just happened "organically".
I hope for us all to have a creative New Year, while avoiding disasters which seem to be lurking behind every corner these days...
