Neural networks for Vector Quantization (VQ) such as K-means, Neural-Gas (NG) network and Kohonen's Self-Organizing Map (SOM) have been proposed. K-means, which is a "hard-max" approach, converges very fast. The method, however, devotes itself to local search, and it easily falls into local minima. On the other hand, the NG and SOM methods, which are "soft-max" approaches, are good at the global search ability. Though NG and SOM exhibit better performance in coming close to the optimum than that of K-means, the methods converge slower than K-means. In order to the disadvantages that exist when K-means, NG and SOM are used individually, this paper proposes hybrid methods such as NG-K, SOM-K and SOM-NG. NG-K performs NG adaptation during short period of time early in the learning process, and then the method performs K-means adaptation in the rest of the process. SOM-K and SOM-NG are similar as NG-K. From numerical simulations including an image compression problem, NG-K and SOM-K exhibit better performance than other methods.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Shinya FUKUMOTO, Noritaka SHIGEI, Michiharu MAEDA, Hiromi MIYAJIMA, "A Hybrid Learning Approach to Self-Organizing Neural Network for Vector Quantization" in IEICE TRANSACTIONS on Fundamentals,
vol. E86-A, no. 9, pp. 2280-2286, September 2003, doi: .
Abstract: Neural networks for Vector Quantization (VQ) such as K-means, Neural-Gas (NG) network and Kohonen's Self-Organizing Map (SOM) have been proposed. K-means, which is a "hard-max" approach, converges very fast. The method, however, devotes itself to local search, and it easily falls into local minima. On the other hand, the NG and SOM methods, which are "soft-max" approaches, are good at the global search ability. Though NG and SOM exhibit better performance in coming close to the optimum than that of K-means, the methods converge slower than K-means. In order to the disadvantages that exist when K-means, NG and SOM are used individually, this paper proposes hybrid methods such as NG-K, SOM-K and SOM-NG. NG-K performs NG adaptation during short period of time early in the learning process, and then the method performs K-means adaptation in the rest of the process. SOM-K and SOM-NG are similar as NG-K. From numerical simulations including an image compression problem, NG-K and SOM-K exhibit better performance than other methods.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e86-a_9_2280/_p
Copy
@ARTICLE{e86-a_9_2280,
author={Shinya FUKUMOTO, Noritaka SHIGEI, Michiharu MAEDA, Hiromi MIYAJIMA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Hybrid Learning Approach to Self-Organizing Neural Network for Vector Quantization},
year={2003},
volume={E86-A},
number={9},
pages={2280-2286},
abstract={Neural networks for Vector Quantization (VQ) such as K-means, Neural-Gas (NG) network and Kohonen's Self-Organizing Map (SOM) have been proposed. K-means, which is a "hard-max" approach, converges very fast. The method, however, devotes itself to local search, and it easily falls into local minima. On the other hand, the NG and SOM methods, which are "soft-max" approaches, are good at the global search ability. Though NG and SOM exhibit better performance in coming close to the optimum than that of K-means, the methods converge slower than K-means. In order to the disadvantages that exist when K-means, NG and SOM are used individually, this paper proposes hybrid methods such as NG-K, SOM-K and SOM-NG. NG-K performs NG adaptation during short period of time early in the learning process, and then the method performs K-means adaptation in the rest of the process. SOM-K and SOM-NG are similar as NG-K. From numerical simulations including an image compression problem, NG-K and SOM-K exhibit better performance than other methods.},
keywords={},
doi={},
ISSN={},
month={September},}
Copy
TY - JOUR
TI - A Hybrid Learning Approach to Self-Organizing Neural Network for Vector Quantization
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2280
EP - 2286
AU - Shinya FUKUMOTO
AU - Noritaka SHIGEI
AU - Michiharu MAEDA
AU - Hiromi MIYAJIMA
PY - 2003
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E86-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2003
AB - Neural networks for Vector Quantization (VQ) such as K-means, Neural-Gas (NG) network and Kohonen's Self-Organizing Map (SOM) have been proposed. K-means, which is a "hard-max" approach, converges very fast. The method, however, devotes itself to local search, and it easily falls into local minima. On the other hand, the NG and SOM methods, which are "soft-max" approaches, are good at the global search ability. Though NG and SOM exhibit better performance in coming close to the optimum than that of K-means, the methods converge slower than K-means. In order to the disadvantages that exist when K-means, NG and SOM are used individually, this paper proposes hybrid methods such as NG-K, SOM-K and SOM-NG. NG-K performs NG adaptation during short period of time early in the learning process, and then the method performs K-means adaptation in the rest of the process. SOM-K and SOM-NG are similar as NG-K. From numerical simulations including an image compression problem, NG-K and SOM-K exhibit better performance than other methods.
ER -