CombNET-III with Nonlinear Gating Network and Its Application in Large-Scale Classification Problems

スポンサーリンク

概要

• 論文の詳細を見る

• Modern applications of pattern recognition generate very large amounts of data, which require large computational effort to process. However, the majority of the methods intended for large-scale problems aim to merely adapt standard classification methods without considering if those algorithms are appropriated for large-scale problems. CombNETII was one of the first methods specifically proposed for such kind of a task. Recently, an extension of this model, named CombNET-III, was proposed. The main modifications over the previous model was the substitution of the expert networks by Support Vectors Machines (SVM) and the development of a general probabilistic framework. Although the previous models performance and flexibility were improved, the low accuracy of the gating network was still compromising CombNET-IIIs classification results. In addition, due to the use of SVM based experts, the computational complexity is higher than CombNET-II. This paper proposes a new two-layered gating network structure that reduces the compromise between number of clusters and accuracy, increasing the models performance with only a small complexity increase. This high-accuracy gating network also enables the removal the low confidence expert networks from the decoding procedure. This, in addition to a new faster strategy for calculating multiclass SVM outputs significantly reduced the computational complexity. Experimental results of problems with large number of categories show that the proposed model outperforms the original CombNET-III, while presenting a computational complexity more than one order of magnitude smaller. Moreover, when applied to a database with a large number of samples, it outperformed all compared methods, confirming the proposed models flexibility.

• （社）電子情報通信学会の論文
• 2008-02-01

著者

• Kugler Mauricio

  Nagoya Inst. Technol. Nagoya‐shi Jpn

• Kugler Mauricio

  The Department Of Computer Science & Engineering Nagoya Institute Of Technology

• KUROYANAGI Susumu

  the Department of Computer Science & Engineering, Nagoya Institute of Technology

• NUGROHO Anto

  Agency for the Assessment and Application of Technology (PTIK-BPPT)

• IWATA Akira

  the Department of Computer Science & Engineering, Nagoya Institute of Technology

• Iwata A

  Department Of Computer Science & Engineering Nagoya Institute Of Technology

• Iwata Akira

  The Department Of Computer Science & Engineering Nagoya Institute Of Technology

• Kuroyanagi S

  The Department Of Computer Science & Engineering Nagoya Institute Of Technology

関連論文

• Robust Method for Recovering Sign of Gaussian Curvature from Multiple Shading Images(Special Issue on Machine Vision Applications)
• Classification of Surface Curvature from Shading Images Using Neural Network
• CombNET-III with Nonlinear Gating Network and Its Application in Large-Scale Classification Problems
• CombNET-III: A Support Vector Machine Based Large Scale Classifier with Probabilistic Framework(Pattern Recognition)
• A Solution for Imbalanced Training Sets Problem by CombNET-II and Its Application on Fog Forecasting
• Edge Detection Using Neural Network for Non-uniformly llluminated Images
• A Character-Based Postprocessing System for Handwritten Japanese Address Recognition

スポンサーリンク