In-reply-to » I sent you my QR code, please respond! Media *for context: long ago, there were some complaints, about some of my sitting drawings, where the legs are apart, not using dithering/more shading and one of my favourite artists, made a video, exploring the use of QR codes, in art P.S.: the code just redirects to my websites

Source of inspiration:
https://youtu.be/TlafDammd6s

​ Read More

i wish it was realistic for me to learn golang but every single time i try to comprehend any go code i’m like What the fuck am i looking at. why is all of this so short and condensed GIVE ME VERBOSE CODE

​ Read More

I sent you my QR code, please respond!

*for context: long ago, there were some complaints, about some of my sitting drawings, where the legs are apart, not using dithering/more shading and one of my favourite artists, made a video, exploring the use of QR codes, in art
P.S.: the code just redirects to my websites

​ Read More
In-reply-to » Over the past few weeks I've been experimenting with and doing some deep learning and researching into neutral networks and evolutionary adaptation of them. The thing is I haven't gotten very far. I've been able to build two different approaches so far with limited results. The frustrating part is that these things are so "random" it isn't even funny. Like I can't even get a basic ANN + GA to evolve a network that solves the XOR pattern every time with high levels of accuracy. 😞

Jokes aside, what’s the aim for doing this? Other than learning something new, that is.

​ Read More
In-reply-to » Over the past few weeks I've been experimenting with and doing some deep learning and researching into neutral networks and evolutionary adaptation of them. The thing is I haven't gotten very far. I've been able to build two different approaches so far with limited results. The frustrating part is that these things are so "random" it isn't even funny. Like I can't even get a basic ANN + GA to evolve a network that solves the XOR pattern every time with high levels of accuracy. 😞

@prologic@twtxt.net so, what did you have for dinner last night? How’s the weather Down Under a bit past 02:00? Do tell me. 🀭

​ Read More
In-reply-to » Over the past few weeks I've been experimenting with and doing some deep learning and researching into neutral networks and evolutionary adaptation of them. The thing is I haven't gotten very far. I've been able to build two different approaches so far with limited results. The frustrating part is that these things are so "random" it isn't even funny. Like I can't even get a basic ANN + GA to evolve a network that solves the XOR pattern every time with high levels of accuracy. 😞

This is one of my attempts:

$ go build ./cmd/xor/... && ./xor
Generation  95 | Fitness: 0.999964 | Nodes: 9   | Conns: 19
Target reached!

Best network performance:
  [0 0] β†’ got=0 exp=0 (raw=0.000) βœ…
  [0 1] β†’ got=1 exp=1 (raw=0.990) βœ…
  [1 0] β†’ got=1 exp=1 (raw=0.716) βœ…
  [1 1] β†’ got=0 exp=0 (raw=0.045) βœ…
Overall accuracy: 100.0%
Wrote best.dot – render with `dot -Tpng best.dot -o best.png`

​ Read More

Over the past few weeks I’ve been experimenting with and doing some deep learning and researching into neutral networks and evolutionary adaptation of them. The thing is I haven’t gotten very far. I’ve been able to build two different approaches so far with limited results. The frustrating part is that these things are so β€œrandom” it isn’t even funny. Like I can’t even get a basic ANN + GA to evolve a network that solves the XOR pattern every time with high levels of accuracy. 😞

​ Read More