A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure
This paper attempts to solve the typical problems of self-organizing growing network models, i.e. (a) an influence of the order of input data on the self-organizing ability, (b) an instability to high-dimensional data and an excessive sensitivity to noise, and (c) an expensive computational cost by...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
World Scientific Publishing
2019
|
| Subjects: |
| _version_ | 1825722174063771648 |
|---|---|
| author | Masuyama, Naoki Loo, Chu Kiong Wermter, Stefan |
| author_facet | Masuyama, Naoki Loo, Chu Kiong Wermter, Stefan |
| author_sort | Masuyama, Naoki |
| collection | UM |
| description | This paper attempts to solve the typical problems of self-organizing growing network models, i.e. (a) an influence of the order of input data on the self-organizing ability, (b) an instability to high-dimensional data and an excessive sensitivity to noise, and (c) an expensive computational cost by integrating Kernel Bayes Rule (KBR) and Correntropy-Induced Metric (CIM) into Adaptive Resonance Theory (ART) framework. KBR performs a covariance-free Bayesian computation which is able to maintain a fast and stable computation. CIM is a generalized similarity measurement which can maintain a high-noise reduction ability even in a high-dimensional space. In addition, a Growing Neural Gas (GNG)-based topology construction process is integrated into the ART framework to enhance its self-organizing ability. The simulation experiments with synthetic and real-world datasets show that the proposed model has an outstanding stable self-organizing ability for various test environments. © 2019 World Scientific Publishing Company. |
| first_indexed | 2024-03-06T06:01:37Z |
| format | Article |
| id | um.eprints-24040 |
| institution | Universiti Malaya |
| last_indexed | 2024-03-06T06:01:37Z |
| publishDate | 2019 |
| publisher | World Scientific Publishing |
| record_format | dspace |
| spelling | um.eprints-240402020-03-19T03:50:02Z http://eprints.um.edu.my/24040/ A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure Masuyama, Naoki Loo, Chu Kiong Wermter, Stefan QA75 Electronic computers. Computer science This paper attempts to solve the typical problems of self-organizing growing network models, i.e. (a) an influence of the order of input data on the self-organizing ability, (b) an instability to high-dimensional data and an excessive sensitivity to noise, and (c) an expensive computational cost by integrating Kernel Bayes Rule (KBR) and Correntropy-Induced Metric (CIM) into Adaptive Resonance Theory (ART) framework. KBR performs a covariance-free Bayesian computation which is able to maintain a fast and stable computation. CIM is a generalized similarity measurement which can maintain a high-noise reduction ability even in a high-dimensional space. In addition, a Growing Neural Gas (GNG)-based topology construction process is integrated into the ART framework to enhance its self-organizing ability. The simulation experiments with synthetic and real-world datasets show that the proposed model has an outstanding stable self-organizing ability for various test environments. © 2019 World Scientific Publishing Company. World Scientific Publishing 2019 Article PeerReviewed Masuyama, Naoki and Loo, Chu Kiong and Wermter, Stefan (2019) A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure. International Journal of Neural Systems, 29 (05). p. 1850052. ISSN 0129-0657, DOI https://doi.org/10.1142/S0129065718500521 <https://doi.org/10.1142/S0129065718500521>. https://doi.org/10.1142/S0129065718500521 doi:10.1142/S0129065718500521 |
| spellingShingle | QA75 Electronic computers. Computer science Masuyama, Naoki Loo, Chu Kiong Wermter, Stefan A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure |
| title | A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure |
| title_full | A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure |
| title_fullStr | A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure |
| title_full_unstemmed | A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure |
| title_short | A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure |
| title_sort | kernel bayesian adaptive resonance theory with a topological structure |
| topic | QA75 Electronic computers. Computer science |
| work_keys_str_mv | AT masuyamanaoki akernelbayesianadaptiveresonancetheorywithatopologicalstructure AT loochukiong akernelbayesianadaptiveresonancetheorywithatopologicalstructure AT wermterstefan akernelbayesianadaptiveresonancetheorywithatopologicalstructure AT masuyamanaoki kernelbayesianadaptiveresonancetheorywithatopologicalstructure AT loochukiong kernelbayesianadaptiveresonancetheorywithatopologicalstructure AT wermterstefan kernelbayesianadaptiveresonancetheorywithatopologicalstructure |