A class density approximation neural network for improving the generalization of Fisherface

J Jiang, L Zhang, T Furukawa - Neurocomputing, 2008 - Elsevier
Fisherface is a popular dimensionality reduction technique in face recognition. The obtained
discriminative subspace, however, may not generalize well to unseen classes, as in the …

Self-organizing homotopy network

T Furukawa - International Workshop on Self-Organizing …, 2007 - biecoll.ub.uni-bielefeld.de
In this paper, we propose a conceptual learning algorithm called the'self-organizing
homotopy (SOH)'together with an implementation thereof. As in the case of the SOM, our …

Multi-task manifold learning using hierarchical modeling for insufficient samples

H Ishibashi, K Higa, T Furukawa - … 13–16, 2018, Proceedings, Part III 25, 2018 - Springer
In this paper, we propose a method for multi-task manifold learning. For a set of tasks of
dimensionality reduction, the aim of the method is to model each given dataset as a …

MODULAR NETWORK SOM (MNSOM): A NEW POWERFUL TOOL IN NEURAL NETWORKS

MA Muslim - TELKOMNIKA (Telecommunication Computing …, 2009 - telkomnika.uad.ac.id
In this paper, a new powerful method in artificial neural networks, called modular network
SOM (mnSOM) is introduced. mnSOM is a generalization of Self Organizing Maps (SOM) …

[PDF][PDF] Segmentation of environment and formation of graph-based maps in mobile robots

MA Muslim - 2008 - Citeseer
Classical artificial intelligence (AI) has faced many difficulties such as the symbol grounding
problem (ie providing relationship between symbols and the real world), the embodiment …

[引用][C] 基于最大散度差判别分析的一种目标识别方法

张善文, 李萍, 井荣枝, 张云龙 - 系统仿真学报, 2013

自己組織化マップの一般化理論とその応用-理論の確立から実用化まで

古川徹生, フルカワテツオ - 2008 - kyutech.repo.nii.ac.jp
はしがき Page 1 1 はしがき 本報告書は平成 17 年度~平成 19 年度科学研究費補助金基盤研究(C)の
助成によって行った 「自己組織化マップの一般化理論とその応用~理論の確立から実用化まで~」の …