A better and #symbolic #deeplearning #algorithm in #commonLisp .
screwlisp.small-web.org/fundam…
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?
#ai #programming #DL
This entry was edited (1 day ago)
Ramin Honary likes this.
screwlisp reshared this.
screwlisp
in reply to screwlisp • • •Edit: I snuck back in and made the predicate being used a keyword arguement so it could be hoovered into the (apply .. keys) in practical use in the example I am writing today.
I also added a references here section, currently indexing into Artyom's toot. screwlisp.small-web.org/fundam…
a better deep learning algorithm in lisp
screwlisp.small-web.orgscrewlisp reshared this.