Spherical SOM and Arrangement of Neurons Using Helix on Sphere

スポンサーリンク

概要

• 論文の詳細を見る

• Self-organizing maps(SOM) are a kind of neural network, and are applied to many fields. In many applications, there are borders surrounding the neuron arrangement. It causes a problem which is called ‘Border effect’ because the number of neighborhood neurons of a neuron near a border is different from that of a neuron near the center. This problem can be solved by arranging neurons uniformly on the surface of a sphere. But by the conventional method we cannot arrange neurons of arbitrary number. Therefore, it is inconvenient to use. Here we developed a method to arrange the neurons of arbitrary number by dividing a helix which covers the surface of a sphere into equal parts. It also can arrange neurons on a sphere more uniformly than the conventional method.

著者

• Altaf-ul-amin Md.

  Nara Institute Of Science And Technology

• KUROKAWA KEN

  Nara Institute of Science and Technology, Graduate School of Information Science

• KANAYA SHIGEHIKO

  Nara Institute of Science and Technology, Graduate School of Information Science

• Kanaya Shigehiko

  Nara Institute Of Science And Technology Graduate School Of Information Science

• Nishio Hirokazu

  Nara Institute Of Science And Technology Graduate School Of Information Science

• Altaf-Ul-Amin Md.

  Nara Institute of Science and Technology, Graduate School of Information Science

関連論文

• Metabolic pathway prediction based on inclusive relation between cyclic substructures
• KNApSAcK gene classification system for Arabidopsis thaliana : Comparative genomic analysis of unicellular to seed plants
• Predicting conformation of protein complexes by determining statistically significant domain-domain interactions
• An approach to peak detection in GC-MS chromatograms and application of KNApSAcK database in prediction of candidate metabolites
• Design for Two-Pattern Testability of Controller-Data Path Circuits
• Elucidating Conservation of Genes in Multiple Genomes Based on Graphs Configured by Bidirectional Best-Hit Relationships
• Comparison of Protein Complexes Predicted from PPI Networks by DPClus and Newman Clustering Algorithms
• Spherical SOM and Arrangement of Neurons Using Helix on Sphere (特集:第11回MPSシンポジウム--複雑系の科学とその応用)
• A tool for high-throughput prediction of molecular formulas and identification of isotopic peaks from large-scale mass spectrometry data
• Toward genome-wide metabolotyping and elucidation of metabolic system : metabolic profiling of large-scale bioresources
• Visualization of metabolite identifier information
• Elucidating Conservation of Genes in Multiple Genomes Based on Graphs Configured by Bidirectional Best-Hit Relationships
• Spherical SOM and Arrangement of Neurons Using Helix on Sphere
• Elucidating Conservation of Genes in Multiple Genomes Based on Graphs Configured by Bidirectional Best-Hit Relationships

もっと見る 閉じる

スポンサーリンク