Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 노영균 | - |
dc.date.accessioned | 2019-12-04T06:24:09Z | - |
dc.date.available | 2019-12-04T06:24:09Z | - |
dc.date.issued | 2018-01 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v. 40, no. 1, page. 92-105 | en_US |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.issn | 1939-3539 | - |
dc.identifier.uri | https://ieeexplore.ieee.org/document/7847415 | - |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/117285 | - |
dc.description.abstract | Classical discriminant analysis attempts to discover a low-dimensional subspace where class label information is maximally preserved under projection. Canonical methods for estimating the subspace optimize an information-theoretic criterion that measures the separation between the class-conditional distributions. Unfortunately, direct optimization of the information-theoretic criteria is generally non-convex and intractable in high-dimensional spaces. In this work, we propose a novel, tractable algorithm for discriminant analysis that considers the class-conditional densities as interacting fluids in the high-dimensional embedding space. We use the Bhattacharyya criterion as a potential function that generates forces between the interacting fluids, and derive a computationally tractable method for finding the low-dimensional subspace that optimally constrains the resulting fluid flow. We show that this model properly reduces to the optimal solution for homoscedastic data as well as for heteroscedastic Gaussian distributions with equal means. We also extend this model to discover optimal filters for discriminating Gaussian processes and provide experimental results and comparisons on a number of datasets. | en_US |
dc.description.sponsorship | YKN is supported by grants from NSRI, BK21Plus, MITIP-10048320, AFOSR, JHH from OFRN-C4ISR, NSF IIS EAGER 1550757, FCP from BK21Plus, MITIP-10048320, BMRR, Soft Robot ERC, BTZ from IITP-R0126-16-1072, KEIT-10060086, KEIT-10044009, and DDL from the U.S. NSF, ONR, ARL, AFOSR, DOT, DARPA. | en_US |
dc.language.iso | en_US | en_US |
dc.publisher | IEEE COMPUTER SOC | en_US |
dc.subject | Discriminant analysis | en_US |
dc.subject | dimensionality reduction | en_US |
dc.subject | fluid dynamics | en_US |
dc.subject | Gauss principle of least constraint | en_US |
dc.subject | Gaussian processes | en_US |
dc.title | Fluid Dynamic Models for Bhattacharyya-Based Discriminant Analysis | en_US |
dc.type | Article | en_US |
dc.relation.no | 1 | - |
dc.relation.volume | 40 | - |
dc.identifier.doi | 10.1109/TPAMI.2017.2666148 | - |
dc.relation.page | 92-105 | - |
dc.relation.journal | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.contributor.googleauthor | Noh, Yung-Kyun | - |
dc.contributor.googleauthor | Hamm, Jihun | - |
dc.contributor.googleauthor | Park, Frank Chongwoo | - |
dc.contributor.googleauthor | Zhang, Byoung-Tak | - |
dc.contributor.googleauthor | Lee, Daniel D. | - |
dc.relation.code | 2018002038 | - |
dc.sector.campus | S | - |
dc.sector.daehak | COLLEGE OF ENGINEERING[S] | - |
dc.sector.department | DEPARTMENT OF COMPUTER SCIENCE | - |
dc.identifier.pid | nohyung | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.