Chill and problem prone (though all of them are overcome) #CommonLisp #lisp #video exhibiting my #binryhop hopfield net package.
https://forth.noip.me:8443/w/23cQQJVTcG6nqsnT8jkgWV

So chill that my package relaxes a lot of constraints on hopfield nets (sure, it can be jagged, rewritable memories, and the memory can be NIL, and the memory can be a subset of of the input or vice versa (????)
About a half hour; would probably be quite good at 2x speed.

Example of debug noodling around in a lisp package a bit.

#CommonLisp #Gopher #binryhop #deepNetworks #asdf
gopher://tilde.institute/1/~screwtape/binry-hop/
https://gopher.floodgap.com/gopher/gw.lite?=tilde.institute+70+312f7e7363726577746170652f62696e72792d686f702f
gopher://gopher.club/1/users/screwtape/
https://gopher.floodgap.com/gopher/gw.lite?=gopher.club+70+312f75736572732f7363726577746170652f

I was redeveloping my nascent binry-hop deep hopfield network package to use package-inferred-system, so different sorts of components and data (text of book)? Could be cooked into one overarching system but loaded separately.

I'm happy with it; and I believe in using asdf strongly idiomatically. Commentary?

#AI #DeepLearning #HopfieldNetworks (My rudimentary package is named #binryhop ; a pun on bunny-hop and binary hopfield ).
So I had an idea. What if I take two source images: A fish and a tree, thresholded. The fish and tree are roughly the same resolution as an image screwtape-fish-tree I will draw. I griddle the high resolution images into 90x90 regions. Then, I make the fish and tree grid pieces my memories and simply run each swatch of my own image through some updates.