And I think if you had a 4 view visualization of 4 perspectives, it would reveal algorithm behavior to viewers more easily, because the random rotations are very distracting for teaching / illustrative purposes.
Plus, the convergence of the grid apparently shows some undesirable folding of multiple gridpoints on the same target point. Better Kohonnen mappers often try to make the grid smoothly conformal, when the points are not clustered at heirarchical scales, unlike your target points that are relatively evenly spread.
WOW, it looks like a very slow neural network algorithm for it's use of tens of hundreds of learning cycles with non-monotonic convergence. Maybe if you used NN radial basis functions and cluster convex hull characterization the convergence could be faster. It is not like it has to even worry about degenerate point clustering with multiple overlapping points of heirarchically packed densities like little solar systems spread in a loose open cluster of stars.
this kind of neuronal Network is a kohonen-map or self-organzing map. you can find source for c++ and java and for other languages. in basic its a really easy kind, and easy cool and easy to make visualiation
Very neat, is it trying to reduce the overall number of faces needed to reach all the points? I'm just curious about the behavior that I'm seeing in the later generations.
theres lot of free stuff,but i doubt they are better than matlab or mathematica.
I could make a complete machine control software in 20 lines of code in MAtlab.
Scilab or Pylab ,and most free alternatives for other commercial software usually have a lack of seamless integration like commercial solutions.
jeetendrag10acc2 6 months ago
ffs shut the turning i can see it from one angle as well Oo
lucb1e 1 year ago 5
what is the music?
phatsmanto99 2 years ago
When programming a java neural net program do you use a neural net library and is so where do you download it.
Fusionicon 2 years ago
comment typo fix: "- like your target points that are relatively evenly spread"
rubbercraft 2 years ago
And I think if you had a 4 view visualization of 4 perspectives, it would reveal algorithm behavior to viewers more easily, because the random rotations are very distracting for teaching / illustrative purposes.
rubbercraft 2 years ago
Plus, the convergence of the grid apparently shows some undesirable folding of multiple gridpoints on the same target point. Better Kohonnen mappers often try to make the grid smoothly conformal, when the points are not clustered at heirarchical scales, unlike your target points that are relatively evenly spread.
rubbercraft 2 years ago
WOW, it looks like a very slow neural network algorithm for it's use of tens of hundreds of learning cycles with non-monotonic convergence. Maybe if you used NN radial basis functions and cluster convex hull characterization the convergence could be faster. It is not like it has to even worry about degenerate point clustering with multiple overlapping points of heirarchically packed densities like little solar systems spread in a loose open cluster of stars.
rubbercraft 2 years ago
I've always been fascinated by AI, but chose to stay away from it as people are dumbasses and we'll just end up with cylons running around!
squidcreek 2 years ago
do u have a matlab source for this?
hakaktulu 3 years ago
matlab is ocmercial shit :)
There are a lot of free better stuff like scillab.. or pylab
I RLY don't understand why matlab is so popular on universites?
artilekt 2 years ago 3
@artilekt Plus QT Octave
marek007able 1 year ago
@artilekt Because it's a industry standard...
TJFFx 1 year ago 2
this kind of neuronal Network is a kohonen-map or self-organzing map. you can find source for c++ and java and for other languages. in basic its a really easy kind, and easy cool and easy to make visualiation
P5ark 2 years ago
Very neat, is it trying to reduce the overall number of faces needed to reach all the points? I'm just curious about the behavior that I'm seeing in the later generations.
BikemsRyan 3 years ago
This comment has received too many negative votes show
Has anyone looked for the answers in "Fractals" for keys to artificial intelligence?
rbolo29 3 years ago
Very cool applet, I like Java and Neural Networks, so I really liked this lol.
msj120 3 years ago
Great beat! What is it? (I like the neural part too ;-))
zweefvlieg 3 years ago
Fairmont - Gazebo
mfunkmann 3 years ago
O.o okay?!
konsaik 3 years ago