Click here to Skip to main content
Click here to Skip to main content

Tagged as

Transform arbitary data into Gaussian Distribution for AI and Genetic algorithms

, 25 Dec 2009 CPOL
Rate this:
Please Sign up or sign in to vote.
The fast Walsh Hadamard transform (WHT) is done using patterns of addition and subtractions.That means it is extremely fast and also the central limit theorem applies. If you transform an array of random numbers the output numbers will have a Gaussian distribution (aka the Normal...
The fast Walsh Hadamard transform (WHT) is done using patterns of addition and subtractions.
That means it is extremely fast and also the central limit theorem applies. If you transform an array of random numbers the output numbers will have a Gaussian distribution (aka the Normal distribution).
The O'Connor transform is a series of WHT's and random permutations (with optional random sign flipping) that converts arbitrary numerical data into data with a Gaussian distribution. It has a lot of uses for Compressive Sensing, Genetic algorithms, Neural Nets and Random projections.
I have extremely fast code here:
Interesting Source Code
There are also some other projects there that are very interesting.
 
Sean O'Connor

License

This article, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

Share

About the Author

sean_vn

United States United States
No Biography provided

Comments and Discussions

 
-- There are no messages in this forum --
| Advertise | Privacy | Terms of Use | Mobile
Web01 | 2.8.141223.1 | Last Updated 25 Dec 2009
Article Copyright 2009 by sean_vn
Everything else Copyright © CodeProject, 1999-2014
Layout: fixed | fluid