experimenting with mandelbrot set and neural network

ker2x

Fractal Molossus

Posts: 795

experimenting with mandelbrot set and neural network

« on: November 15, 2010, 11:36:28 PM »

i tried to program a neural network that try to guess if a complex point is in the mandelbrot set.
The result is... well... bad. (and it's one of my best result) sad

Anyone tried ? anyone know about NN ?


	Logged

often times... there are other approaches which are kinda crappy until you put them in the context of parallel machines
(en) http://www.blog-gpgpu.com/ , (fr) http://www.keru.org/ ,
Sysadmin & DBA @ http://www.over-blog.com/

cKleinhuis

Administrator
Fractal Senior

Posts: 7044

formerly known as 'Trifox'

Re: experimenting with mandelbrot set and neural network

« Reply #1 on: November 16, 2010, 12:10:22 AM »

lol, funny application, just keep it running wink

how many neurons do u use for that ?
i think that a basic set up cannot lead to impressive results, but the overall shape is visible, so the system may has learned something,
it will always be kinda "unsharp", if the method would be fast enough for a point to decide it is inside/outside, and any of those 2 can give
valid results, the other variant can be calculated, perhaps you should train your nn for detecting points that are OUTSIDE ?

regards


	Logged

---

divide and conquer - iterate and rule - chaos is No random!

Jesse

Download Section
Fractal Schemer

Posts: 1013

Re: experimenting with mandelbrot set and neural network

« Reply #2 on: November 16, 2010, 12:19:34 AM »

A rough shape should work, of course a chaotic function that gives different results for very near points needs to much information storage.
You need a good way to feed the network, maybe not just x and y, but a precomputed value... hmm like 10 iterations of the formula wink

I already thought of a neural network as configurable formula for one iteration... so you could varify the weights and choose yourself if its getting better to find some interesting stuff...


	Logged

Pages: [1] Go Down

« previous next »

	Author	Topic: experimenting with mandelbrot set and neural network (Read 2862 times)
		Description:
0 Members and 1 Guest are viewing this topic.

Related Topics
	Subject	Started by	Replies	Views	Last post
	(it works!) Neural Network, Self Organizing Map, and Mandelbrot Set Programming	ker2x	12	5174	November 23, 2010, 07:27:13 PM by ker2x
	Biomechanical Neural Network Mandelbulb3D Gallery	dainbramage	0	1210	June 29, 2011, 12:28:18 PM by dainbramage
	Experimenting with dIFS..... Images Showcase (Rate My Fractal)	reactorman	0	1071	October 25, 2013, 09:24:52 PM by reactorman
	Neural Network Fractal Science Kit Gallery	Ross Hilbert	0	1349	December 12, 2013, 06:07:28 PM by Ross Hilbert
	Neural Network Images Showcase (Rate My Fractal)	Lois	0	782	July 01, 2016, 07:15:57 PM by Lois

END OF AN ERA, FRACTALFORUMS.COM IS CONTINUED ON FRACTALFORUMS.ORG

it was a great time but no longer maintainable by c.Kleinhuis contact him for any data retrieval,
thanks and see you perhaps in 10 years again

The All New FractalForums is now in Public Beta Testing! Visit FractalForums.org and check it out!

	Welcome, Guest. Please login or register.	November 20, 2025, 07:48:26 AM
		Login with username, password and session length

END OF AN ERA, FRACTALFORUMS.COM IS CONTINUED ON FRACTALFORUMS.ORG

it was a great time but no longer maintainable by c.Kleinhuis contact him for any data retrieval, thanks and see you perhaps in 10 years again

The All New FractalForums is now in Public Beta Testing! Visit FractalForums.org and check it out!

it was a great time but no longer maintainable by c.Kleinhuis contact him for any data retrieval,
thanks and see you perhaps in 10 years again