A neural network programming channel

not figuring out why random images are classified as CLOCKS by mobilenet, possibly now with saliency

livestream using keras' embedding layer for first time

decomposing small nns for an hour

hand programming mlps!

Nonlinear boolean functions and their distance to the set of linear boolean functions

if you try to run a small neural net backwards by hand

linear threshold functions are always 37.5% correlated with an input??

implementing a cool idea for small binary nn visualizer p3

mumblecode - why closest linear functions to random function all flip same input??

making small mlps wo gradscent and then compare with gradscent pt 2 (hot gpt4o action)

prgrm nn maybe

ltfs with 0 bias, positive sorted weights, how different can they be?

if you have boolean circuit with only majority and inputs, what it is that like

neural nets HATE this simple 3d geometric transform

implementing a cool idea for small binary nn visualizer p2

implementing new circuits experiment

hand setting neural net weights

linear threshold functions are always 37.5% correlated with an input

linear threshold functions are always 37.5% correlated with an input??

does "separating negation pairs" entirely distinguish linear vs nonlinear boolean functions??

Making a small neural net chase a larger neural net

trying to get a neural net to learn the identity function (tensorflow.js)

implementing a cool idea for small binary nn visualizer

mumblecode - largely incoherent debugging and then cool vis of nonlinearities in boolean functions

trying to grok 4-bit circuits/mlps

implication structure of ltfs with 0 bias and sorted weights