CombNET-III: A Support Vector Machine Based Large Scale Classifier with Probabilistic Framework(Pattern Recognition)
スポンサーリンク
概要
- 論文の詳細を見る
Several research fields have to deal with very large classification problems, e.g. handwritten character recognition and speech recognition. Many works have proposed methods to address problems with large number of samples, but few works have been done concerning problems with large numbers of classes. CombNET-II was one of the first methods proposed for such a kind of task. It consists of a sequential clustering VQ based gating network (stem network) and several Multilayer Perceptron (MLP) based expert classifiers (branch networks). With the objectives of increasing the classification accuracy and providing a more flexible model, this paper proposes a new model based on the CombNET-II structure, the CombNET-III. The new model, intended for, but not limited to, problems with large number of classes, replaces the branch networks MLP with multiclass Support Vector Machines (SVM). It also introduces a new probabilistic framework that outputs posterior class probabilities, enabling the model to be applied in different scenarios (e.g. together with Hidden Markov Models). These changes permit the use of a larger number of smaller clusters, which reduce the complexity of the final classifiers. Moreover, the use of binary SVM with probabilistic outputs and a probabilistic decoding scheme permit the use of a pairwise output encoding on the branch networks, which reduces the computational complexity of the training stage. The experimental results show that the proposed model outperforms both the previous model CombNET-II and a single multiclass SVM, while presenting considerably smaller complexity than the latter. It is also confirmed that CombNET-III classification accuracy scales better with the increasing number of clusters, in comparison with CombNET-II.
- 社団法人電子情報通信学会の論文
- 2006-09-01
著者
-
Kugler Mauricio
Nagoya Inst. Technol. Nagoya‐shi Jpn
-
Kugler Mauricio
Department Of Computer Science & Engineering Nagoya Institute Of Technology
-
NUGROHO Anto
Agency for the Assessment and Application of Technology (PTIK-BPPT)
-
KUROYANAGI Susumu
Department of Computer Science & Engineering, Nagoya Institute of Technology
-
NUGROHO Anto
School of Life System Science & Technology, Chukyo University
-
IWATA Akira
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)
- Chronic, Traumatic Intraconal Hematic Cyst of the Orbit Removed Through the Fronto-orbital Approach : Case Report
- A Method of an Effective Learning for BP Network from the Data Which Contain Usual or Unusual Data
- 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
- An Inference of the Human Tastes Evaluation by an Artificial Neural Network
- Thermal Preconditioning Attenuates Exercise-induced Muscle Injury in Mice
- Auditory Pulse Neural Network Model to Extract the Inter-Aural Time and Level Difference for Sound Localization (Special Issue on Neurocomputing)
- A Character-Based Postprocessing System for Handwritten Japanese Address Recognition
- Handwritten Postal Code Recognition by Neural Network : A Comparative Study (Special Issue on Character Recognition and Document Understanding)
- Carbon Dioxide-rich Water Bathing Increases Myonuclear Number and Muscle Fiber Size in Regenerating Skeletal Muscles