An annotated example of a simple #symbolic #neuralnetwork written in #commonlisp, with a bunch of comments to help understand data flow.
Thanks @screwlisp for the implementation!
An annotated example of a simple #symbolic #neuralnetwork written in #commonlisp, with a bunch of comments to help understand data flow.
Thanks @screwlisp for the implementation!
3D symbolics!
My #lisp #symbolic #deepLearning #ffnn #condition streamlined.
https://screwlisp.small-web.org/conditions/lisp-symbolic-deep-learning-streamlined/
The pretty and overtly useable rewrite of my earlier brace of articles.
An important condition handling style mistake I cleaned up was that I had previously put HANDLER-BIND /inside/ my INFER. But this freezes it in place; I might as well have used functions as such. Now the algorithm graph is essentially the condition handlers and restarts outside the function at runtime.
#lispyGopherClimate #lisp #technology #podcast #archive, #climate #haiku by @kentpitman
https://communitymedia.video/w/c3GdAXe7BQTbK3VrcXCm7E
& @ramin_hal9001
On the #climate I would like to talk about the company that found #curl and #openssl's #deeplearning many (10ish) 0-day vulns "using #ai ". (#llm s were involved).
This obviously relates to my #lisp #symbolic #DL https://screwlisp.small-web.org/conditions/symbolic-d-l/ (ffnn equiv). Thanks to everyone involved with that so far.
I implemented that using #commonLisp #condition handling viz KMP.
https://screwlisp.small-web.org/conditions/symbolic-d-l/
#Symbolic #deepLearning #inferencing with #commonLisp #conditions
The #DL from before, but it works via a mixture of condition handlers and restarts.
This turned out to be condition example boilerplate, but it was interesting to me personally, at least!
Not sure about this construction I used (paraphrasing):
(prog ((c nil))
start
(restart-case
(if c
(signal c))
(resignal (condition) (setq c condition) (go start))))
https://toobnix.org/w/9oA5WZEkbjKkfbsSxEoJ8v #archive
Okay I guess on the hour it's the Sunday-morning-in-Europe #lispyGopherClimate .
a. I will lightly go over my recent #commonLisp #symbolic #DL ( #ai!) algo / article.
b. Excitingly that gave me occasion to use
(this-function foo &rest keys &key &allow-other-keys)
which I used to pass data-like parameters along without cluttering up arguements (waters' functions of seven arguments). People had tried to explain it to me previously but now I underst
A better and #symbolic #deeplearning #algorithm in #commonLisp .
https://screwlisp.small-web.org/fundamental/a-better-deep-learning-algorithm/
I hope I come across as slightly tongue-in-cheek! Though all my points and notes are in fact genuine.
tl;dr I define completely explainable and interpretable deep learning / inferencing in terms of operations on sets of symbols.
I think it successfully underscores the wild misapprehensions about deep learning that abound in the wild. What do you think?
Enough with #symbolic #protests which achieve nothing we need mass protests demanding legislators move on #impeachment of #KristiNoem, #StephenMiller and #Trump
https://apnews.com/article/no-kings-protest-alex-pretti-minneapolis-immigration-0b34386da0bb3eeac939d9f934680b6c?utm_source=firefox-newtab-en-us #fascism #ice #minneapolis
Friends of GNOME didn't sleep over the holidays, so I have a gap to catch. Still nowhere near the old fixed weight devkit coverage.
https://teams.pages.gitlab.gnome.org/Design/icon-development-kit/index.html