Concerning the differentiability of the energy function in vector quantization algorithms

Details Concerning the differentiability of the energy function in vector quantization algorithms Concerning the differentiability of the energy function in vector quantization algorithms

2006-04-11

arxiv.org/abs/cs/0604046v1

Computer Science

Learning

Under submission to a peer-reviewed international journal

Scientific paper

The adaptation rule for Vector Quantization algorithms, and consequently the convergence of the generated sequence, depends on the existence and properties of a function called the energy function, defined on a topological manifold. Our aim is to investigate the conditions of existence of such a function for a class of algorithms examplified by the initial ''K-means'' and Kohonen algorithms. The results presented here supplement previous studies and show that the energy function is not always a potential but at least the uniform limit of a series of potential functions which we call a pseudo-potential. Our work also shows that a large number of existing vector quantization algorithms developped by the Artificial Neural Networks community fall into this category. The framework we define opens the way to study the convergence of all the corresponding adaptation rules at once, and a theorem gives promising insights in that direction. We also demonstrate that the ''K-means'' energy function is a pseudo-potential but not a potential in general. Consequently, the energy function associated to the ''Neural-Gas'' is not a potential in general.

Affiliated with

Also associated with

No associations

Rating

Concerning the differentiability of the energy function in vector quantization algorithms does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Concerning the differentiability of the energy function in vector quantization algorithms, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Concerning the differentiability of the energy function in vector quantization algorithms will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-286279