Jump to content

Neural network voronoi tesselation


Recommended Posts

  • Moderators

To see whats happening inside a learning neural network, this demo uses voronoi cells as a visualisation tool

 

Based on the iris dataset this network has 4 input, 7 hidden and 3 output neurons

which equates to 49 connections or weights.

 

Push the Train button

Weights change by learning. Every weight is a voronoi cell and represents its value

 

Usually the network will settle after an initial frenzy into a stable state reasonably quickly.

However sometimes 2 or more weights (voronoi cells) compete for supremacy for longer

 

there is always a winner though, sort of mesmerising to watch

 

code

Link to post
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...