Rank: 1211 based on 112 downloads (last 30 days) and 4 files submitted
photo

Kye Taylor

E-mail

Personal Profile:

 

Watch this Author's files

 

Files Posted by Kye Taylor View all
Updated   File Tags Downloads
(last 30 days)
Comments Rating
18 Jun 2013 Screenshot Draw or add axes to figure Super helpful way to visualize axes in a 2D figure. Author: Kye Taylor demo, visualization, axes, axis, x, y 8 1
02 Apr 2013 Screenshot Color-balance demo with GPU computing Use GPU in MATLAB to perform white-balance operation to input image. Author: Kye Taylor graphical processing ..., gpu, high performance comp..., demo, image processing 39 0
17 Apr 2012 Screenshot Laplacian eigenmap ~ Diffusion map ~ manifold learning Demo techniques of nonlinear eigenmaps for the purpose of recovering low-dimensional geometries. Author: Kye Taylor laplacian eigenmap, diffusion map, spectral clustering, lowdimensional geomet..., how to add some image... 56 4
  • 5.0
5.0 | 1 rating
01 Sep 2011 Screenshot Color code a scatter plot Color code a scatter plot in one, two, or three dimensions according to scalar function of the data. Author: Kye Taylor data exploration, plot, scatter plot, highdimensional visua... 9 1
  • 3.0
3.0 | 1 rating
Comments and Ratings by Kye Taylor View all
Updated File Comments Rating
19 Jun 2013 Draw or add axes to figure Super helpful way to visualize axes in a 2D figure. Author: Kye Taylor

t = -1:.1:1;
plot(t,t), drawAxes

13 Dec 2012 Laplacian eigenmap ~ Diffusion map ~ manifold learning Demo techniques of nonlinear eigenmaps for the purpose of recovering low-dimensional geometries. Author: Kye Taylor

First, note that these type of algorithms use the eigenvectors of a diffusion operator to map the data to a new space. The diffusion operator is N-by-N, where N is the number of points in the dataset, so there are N possible eigenvectors to use in this mapping. Typically much fewer than N eigenvectors are used in practice because 1.) reducing dimensionality means you want fewer coordinates to describe each point and 2.) the number of degrees of freedom in a geometrically structured dataset are typically less than the number of points, making dimensionality reduction possible. It turns out that you want the eigenvectors associated with one of the diffusion operators spectrum, depending on how it is defined.

As I've defined it, the diffusion operator (matrix DO) is a sparse matrix (very few nonzero entries) so I use eigs to compute eigenvectors... DO also has eigenvalues that are real and less than or equal to 1. So I ask eigs for the 10 largest algebraic ('la') nvec eigenpairs.

18 Apr 2012 Laplacian eigenmap ~ Diffusion map ~ manifold learning Demo techniques of nonlinear eigenmaps for the purpose of recovering low-dimensional geometries. Author: Kye Taylor

Although the implementation is more in line with Laplacian eigenmaps, I chose to include "diffusion map" in the title since the concept is the same.

Comments and Ratings on Kye Taylor's Files View all
Updated File Comment by Comments Rating
05 May 2014 Color code a scatter plot Color code a scatter plot in one, two, or three dimensions according to scalar function of the data. Author: Kye Taylor Tor Eivind

Hi! Neat code. It would be very beneficial if you included code for the legend(some way of linking the color to the values)

19 Jun 2013 Draw or add axes to figure Super helpful way to visualize axes in a 2D figure. Author: Kye Taylor Kye Taylor

t = -1:.1:1;
plot(t,t), drawAxes

18 May 2013 Laplacian eigenmap ~ Diffusion map ~ manifold learning Demo techniques of nonlinear eigenmaps for the purpose of recovering low-dimensional geometries. Author: Kye Taylor Shuai

09 Apr 2013 Laplacian eigenmap ~ Diffusion map ~ manifold learning Demo techniques of nonlinear eigenmaps for the purpose of recovering low-dimensional geometries. Author: Kye Taylor PK

how to add some image to this code to check dimensionality reduction

13 Dec 2012 Laplacian eigenmap ~ Diffusion map ~ manifold learning Demo techniques of nonlinear eigenmaps for the purpose of recovering low-dimensional geometries. Author: Kye Taylor Kye Taylor

First, note that these type of algorithms use the eigenvectors of a diffusion operator to map the data to a new space. The diffusion operator is N-by-N, where N is the number of points in the dataset, so there are N possible eigenvectors to use in this mapping. Typically much fewer than N eigenvectors are used in practice because 1.) reducing dimensionality means you want fewer coordinates to describe each point and 2.) the number of degrees of freedom in a geometrically structured dataset are typically less than the number of points, making dimensionality reduction possible. It turns out that you want the eigenvectors associated with one of the diffusion operators spectrum, depending on how it is defined.

As I've defined it, the diffusion operator (matrix DO) is a sparse matrix (very few nonzero entries) so I use eigs to compute eigenvectors... DO also has eigenvalues that are real and less than or equal to 1. So I ask eigs for the 10 largest algebraic ('la') nvec eigenpairs.

Contact us