Sunday, March 8, 2009

Self-organizing maps

I'm currently following a course at CMU on neural networks. This post explores learning a 2D embedding of a complex perceptual spacing using self-organizing maps. These outputs were computed using the Lightweight Efficient Network Simulator. The learned embedding makes it possible to wander randomly through the latent low-dimensional manifold underlying the structure in high-dimensional data, e.g. human poses


 
 
 

… or MNIST handwritten digits


No comments:

Post a Comment