Jump to content

File:A317e36 attractor.png

Page contents not supported in other languages.
This is a file from the Wikimedia Commons
From Wikipedia, the free encyclopedia

Original file (1,438 × 1,444 pixels, file size: 2.31 MB, MIME type: image/png)

Summary

Description
English: My entry is an image of a strange attractor. It is an example of the many beautiful and complex chaotic structures that can be obtained from recursive nonlinear systems. A strange attractor shows that the behavior of some deterministic nonlinear systems can, in the short term, be predicted, even though, in the long term, the behavior appears to be random. Here, the image displays the chaotic behavior of a simple recursive neural network. This neural network produces a series of 10 million output values, x(n). Each new value is computed using nonlinear operations on the previous 3 x(n) values.The image is made by plotting x(n) vs x(n-1) for all n greater than 1.
Date
Source Own work
Author Wiscdragon

Licensing

I, the copyright holder of this work, hereby publish it under the following license:
w:en:Creative Commons
attribution
This file is licensed under the Creative Commons Attribution 4.0 International license.
You are free:
  • to share – to copy, distribute and transmit the work
  • to remix – to adapt the work
Under the following conditions:
  • attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.


Captions

This is a strange attractor obtained from a recursive neural network

Items portrayed in this file

depicts

1 May 2021

image/png

1f7d99b3fa832a676a8e47f6328090dabfb75b4a

2,422,325 byte

1,444 pixel

1,438 pixel

File history

Click on a date/time to view the file as it appeared at that time.

Date/TimeThumbnailDimensionsUserComment
current16:28, 30 December 2021Thumbnail for version as of 16:28, 30 December 20211,438 × 1,444 (2.31 MB)WiscdragonUploaded own work with UploadWizard

Metadata