Concerning the differentiability of the energy function in vector quantization algorithms

04/11/2006
by   Dominique Lepetz, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/05/2016

Towards the Limit of Network Quantization

Network quantization is one of network compression techniques to reduce ...
research
05/22/2019

Eigen Artificial Neural Networks

This work has its origin in intuitive physical and statistical considera...
research
05/09/2008

Random projection trees for vector quantization

A simple and computationally efficient scheme for tree-structured vector...
research
03/05/2019

Convergence of gradient descent-ascent analyzed as a Newtonian dynamical system with dissipation

A dynamical system is defined in terms of the gradient of a payoff funct...
research
11/14/2019

The Canonical Distortion Measure for Vector Quantization and Function Approximation

To measure the quality of a set of vector quantization points a means of...
research
09/23/2015

A review of learning vector quantization classifiers

In this work we present a review of the state of the art of Learning Vec...
research
07/27/2021

Initial Foundation for Predicting Individual Earthquake's Location and Magnitude by Using Glass-Box Physics Rule Learner

Although researchers accumulated knowledge about seismogenesis and decad...

Please sign up or login with your details

Forgot password? Click here to reset