DC Field | Value | Language |
---|---|---|
dc.contributor.author | 이지운 | - |
dc.date.accessioned | 2024-05-10T16:38:41Z | - |
dc.date.available | 2024-05-10T16:38:41Z | - |
dc.date.issued | 2024 | - |
dc.identifier.other | OAK-2015-10449 | - |
dc.identifier.uri | http://postech.dcollection.net/common/orgView/200000736674 | ko_KR |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/123401 | - |
dc.description | Master | - |
dc.description.abstract | In this thesis, I propose a new and simple model merging method motivated by the mechanism of model ensemble. Previous alignment-based model merging algo- rithms align the unique and dissimilar neurons, which should be preserved to mimic performance of model ensemble. Therefore, I propose Semi-Ensemble, which takes advantage of the extended parameter space to preserve different neurons without inter- polating them. Semi-Ensemble can generate various degrees of over-parameterization, having model merging and model ensemble as special cases, and efficiently imitate characteristics of ensembled prediction such as calibration score. By carefully con- structing the extended joint parameter space, the interpolated model can strike better trade-off between the total number of parameters and model accuracy. | - |
dc.language | eng | - |
dc.title | Semi-Ensemble: A Simple Approach to Over-parameterized Model Interpolation Pohang University of Science and Technology | - |
dc.title.alternative | 세미앙상블: 과매개변수 모델 보간을 위한 간단한 접근 방법 | - |
dc.type | Thesis | - |
dc.contributor.college | 전자전기공학과 | - |
dc.date.degree | 2024- 2 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.