Numerical Evaluation of Incremental Vector Quantization Using Stochastic Relaxation
Summary :
Learning algorithms for Vector Quantization (VQ) are categorized into two types: batch learning and incremental learning. Incremental learning is more useful than batch learning, because, unlike batch learning, incremental learning can be performed either on-line or off-line. In this paper, we develop effective incremental learning methods by using Stochastic Relaxation (SR) techniques, which have been developed for batch learning. It has been shown that, for batch learning, the SR techniques can provide good global optimization without greatly increasing the computational cost. We empirically investigates the effective implementation of SR for incremental learning. Specifically, we consider five types of SR methods: ISR1, ISR2, ISR3, WSR1 and WSR2. ISRs and WSRs add noise input and weight vectors, respectively. The difference among them is when the perturbed input or weight vectors are used in learning. These SR methods are applied to three types of incremental learning: K-means, Neural-Gas (NG) and Kohonen's Self-Organizing Mapping (SOM). We evaluate comprehensively these combinations in terms of accuracy and computation time. Our simulation results show that K-means with ISR3 is the most comprehensively effective among these combinations and is superior to the conventional NG method known as an excellent method.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E87-A No.9 pp.2364-2371
- Publication Date
- 2004/09/01
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Section on Nonlinear Theory and its Applications)
- Category
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
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.
Cite this
Copy
Noritaka SHIGEI, Hiromi MIYAJIMA, Michiharu MAEDA, "Numerical Evaluation of Incremental Vector Quantization Using Stochastic Relaxation" in IEICE TRANSACTIONS on Fundamentals,
vol. E87-A, no. 9, pp. 2364-2371, September 2004, doi: .
Abstract: Learning algorithms for Vector Quantization (VQ) are categorized into two types: batch learning and incremental learning. Incremental learning is more useful than batch learning, because, unlike batch learning, incremental learning can be performed either on-line or off-line. In this paper, we develop effective incremental learning methods by using Stochastic Relaxation (SR) techniques, which have been developed for batch learning. It has been shown that, for batch learning, the SR techniques can provide good global optimization without greatly increasing the computational cost. We empirically investigates the effective implementation of SR for incremental learning. Specifically, we consider five types of SR methods: ISR1, ISR2, ISR3, WSR1 and WSR2. ISRs and WSRs add noise input and weight vectors, respectively. The difference among them is when the perturbed input or weight vectors are used in learning. These SR methods are applied to three types of incremental learning: K-means, Neural-Gas (NG) and Kohonen's Self-Organizing Mapping (SOM). We evaluate comprehensively these combinations in terms of accuracy and computation time. Our simulation results show that K-means with ISR3 is the most comprehensively effective among these combinations and is superior to the conventional NG method known as an excellent method.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e87-a_9_2364/_p
Copy
@ARTICLE{e87-a_9_2364,
author={Noritaka SHIGEI, Hiromi MIYAJIMA, Michiharu MAEDA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Numerical Evaluation of Incremental Vector Quantization Using Stochastic Relaxation},
year={2004},
volume={E87-A},
number={9},
pages={2364-2371},
abstract={Learning algorithms for Vector Quantization (VQ) are categorized into two types: batch learning and incremental learning. Incremental learning is more useful than batch learning, because, unlike batch learning, incremental learning can be performed either on-line or off-line. In this paper, we develop effective incremental learning methods by using Stochastic Relaxation (SR) techniques, which have been developed for batch learning. It has been shown that, for batch learning, the SR techniques can provide good global optimization without greatly increasing the computational cost. We empirically investigates the effective implementation of SR for incremental learning. Specifically, we consider five types of SR methods: ISR1, ISR2, ISR3, WSR1 and WSR2. ISRs and WSRs add noise input and weight vectors, respectively. The difference among them is when the perturbed input or weight vectors are used in learning. These SR methods are applied to three types of incremental learning: K-means, Neural-Gas (NG) and Kohonen's Self-Organizing Mapping (SOM). We evaluate comprehensively these combinations in terms of accuracy and computation time. Our simulation results show that K-means with ISR3 is the most comprehensively effective among these combinations and is superior to the conventional NG method known as an excellent method.},
keywords={},
doi={},
ISSN={},
month={September},}
Copy
TY - JOUR
TI - Numerical Evaluation of Incremental Vector Quantization Using Stochastic Relaxation
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2364
EP - 2371
AU - Noritaka SHIGEI
AU - Hiromi MIYAJIMA
AU - Michiharu MAEDA
PY - 2004
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E87-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2004
AB - Learning algorithms for Vector Quantization (VQ) are categorized into two types: batch learning and incremental learning. Incremental learning is more useful than batch learning, because, unlike batch learning, incremental learning can be performed either on-line or off-line. In this paper, we develop effective incremental learning methods by using Stochastic Relaxation (SR) techniques, which have been developed for batch learning. It has been shown that, for batch learning, the SR techniques can provide good global optimization without greatly increasing the computational cost. We empirically investigates the effective implementation of SR for incremental learning. Specifically, we consider five types of SR methods: ISR1, ISR2, ISR3, WSR1 and WSR2. ISRs and WSRs add noise input and weight vectors, respectively. The difference among them is when the perturbed input or weight vectors are used in learning. These SR methods are applied to three types of incremental learning: K-means, Neural-Gas (NG) and Kohonen's Self-Organizing Mapping (SOM). We evaluate comprehensively these combinations in terms of accuracy and computation time. Our simulation results show that K-means with ISR3 is the most comprehensively effective among these combinations and is superior to the conventional NG method known as an excellent method.
ER -
English
