home.social

#binryhop — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #binryhop, aggregated by home.social.

fetched live
  1. vintage screwlisp account @[email protected] ·

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

    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 1.5x speed.

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

    #commonlisp #lisp #video #binryhop
  2. vintage screwlisp account @[email protected] ·

    #CommonLisp #Gopher #binryhop #deepNetworks #asdf #lisp
    gopher://tilde.institute/1/~sc
    gopher.floodgap.com/gopher/gw.
    gopher://gopher.club/1/users/s
    gopher.floodgap.com/gopher/gw.

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

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

    #commonlisp #gopher #binryhop #deepnetworks #asdf #lisp
  3. vintage screwlisp account @[email protected] ·

    #CommonLisp #Gopher #binryhop #deepNetworks #asdf #lisp
    gopher://tilde.institute/1/~sc
    gopher.floodgap.com/gopher/gw.
    gopher://gopher.club/1/users/s
    gopher.floodgap.com/gopher/gw.

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

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

    #commonlisp #gopher #binryhop #deepnetworks #asdf #lisp
  4. vintage screwlisp account @[email protected] ·

    OK The #binryhop #example #scenarios . #deep #ai #original
    The txt files are eminently viewable ascii art dumps of the output neurons.
    I
    Scenario one. There's only one memory. An input converges to that in one breadth-first pass.
    gopher://tilde.institute/0/~sc
    gopher.floodgap.com/gopher/gw.
    II
    Scenario two. There are five memories. The memories are not spaced out enough, and become stuck in an erroneous stable state.
    gopher.floodgap.com/gopher/gw.

    1/2

    #binryhop #example #scenarios #deep #ai #original
  5. vintage screwlisp account @[email protected] ·

    OK The #binryhop #example #scenarios . #deep #ai #original
    The txt files are eminently viewable ascii art dumps of the output neurons.
    I
    Scenario one. There's only one memory. An input converges to that in one breadth-first pass.
    gopher://tilde.institute/0/~sc
    gopher.floodgap.com/gopher/gw.
    II
    Scenario two. There are five memories. The memories are not spaced out enough, and become stuck in an erroneous stable state.
    gopher.floodgap.com/gopher/gw.

    1/2

    #binryhop #example #scenarios #deep #ai #original
  6. vintage screwlisp account @[email protected] ·

    #binryhop Hopfield net #deepLearning book rough chapter 1
    #gopher phlog about it:
    tilde.institute/0/~screwtape/209661045-rough-chapter-1
    gopher.floodgap.com/gopher/gw.
    Chapter 1:
    gopher://tilde.institute/0/~sc
    gopher.floodgap.com/gopher/gw.
    tl;dr it's the iconic deep learning XOR example, using a hopfield-net-closure-generating common lisp package (at gopher.floodgap.com/gopher/gw. )
    It's at the top of my phlog.

    Help me form my book-writing and deep-learning!

    #binryhop #deeplearning #gopher
  7. vintage screwlisp account @[email protected] ·

    #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.

    #ai #deeplearning #hopfieldnetworks #binryhop
  8. vintage screwlisp account @[email protected] ·

    #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.

    #ai #deeplearning #hopfieldnetworks #binryhop