s1

Comment

Comment by Shahrokh Kamyab on May 28, 2018 at 1:27pm

Hi!
Can you explain the workflow a bit more? you mentioned it's gonna be part of Octopus?

Best regards

Shahrokh

Comment by Robert Vier on December 15, 2015 at 4:25am

The 'field' is a collection of Bipolar Sigmoid Functions. Their coefficients get altered by the algorithm.

The network has

2 input nodes = x|y of point (a point on the curves)

2 output nodes = x|y of assigned direction (the tangent)

and a number of hidden nodes which are fully connected.

Dividing the curves then gives you a number of samples (pairs of inputs with known desired pairs of output values) to figure out some coefficients which minimize the error between inputs and outputs.

The rest is simple RungeKutta4 integration with the trained 'field' giving directions.

A big drawback is that it's not PI-invariant. I cant figure an efficient way to make it ignore the orientation of the input vectors.

Compared to just interpolating the vectors it's also dead slow and inaccurate. But it's an intuitive way to get a grip on what those networks can and cannot do well.

Comment by David Rutten on December 15, 2015 at 3:09am

How is the field defined? Is it a sampling grid? A collection of polynomials? A collection of trig functions?

Comment by Robert Vier on December 15, 2015 at 2:40am

basically the field tries to fit itself to a curve you've drawn. will be part of the next release of octopus

Comment by Tudor Cosmatu on December 15, 2015 at 2:35am

beautiful

Comment by Kellan Shanahan on December 14, 2015 at 4:47pm

Looks fantastic! Meanwhile I translated Alexander's link into GH using Anemone, one can get a variety of forms using the scale input on the Perlin Component.

Comment by Robert Vier on December 14, 2015 at 8:18am

schiele's standing nude with stockings btw

Comment by Alexander on December 14, 2015 at 7:24am

Oh now I understand. Your explanation flew right by me but makes sense now. Trippy. Interesting.

Comment by Robert Vier on December 14, 2015 at 3:39am

nice link! although I'm not doing noise, at least trying :)

Comment by Alexander on December 13, 2015 at 8:39pm

Sweet!

https://flashyprogramming.wordpress.com/2009/12/26/visualizing-perl...