Publications
Detailed Information
A Viewpoint of Algebraic Geometry in Singular Learning Theory : 대수기하학적 관점에서의 특이학습이론
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 김영훈 | - |
dc.contributor.author | 한지혜 | - |
dc.date.accessioned | 2018-05-29T05:07:30Z | - |
dc.date.available | 2018-05-29T05:07:30Z | - |
dc.date.issued | 2018-02 | - |
dc.identifier.other | 000000149283 | - |
dc.identifier.uri | https://hdl.handle.net/10371/142448 | - |
dc.description | 학위논문 (석사)-- 서울대학교 대학원 : 자연과학대학 수리과학부, 2018. 2. 김영훈. | - |
dc.description.abstract | In this thesis, the goal of singular learning theory and its methods are described. To resolve the singularity problem, we will introduce resolution of singularities, the notion in algebraic geometry. In addition, we will go over some examples of singular learning theory (focus on strictly singular model) and show how to resolve singularities by computation. In particular, in the reduced rank regression model, the process of resolution will be described by taking blow-ups. Finally, we will introduce a determinantal variety, and examine the possibility of connection with the reduced rank regression model. | - |
dc.description.tableofcontents | 1. Introduction 1
1.1 Main Results 1 1.2 Introduction 4 2. Preliminaries 12 2.1 Elementary Probability Theory 12 2.2 Statistical Learning Theory 19 2.3 Singularity Theory 26 3. Examples of Singular Learning Theory 33 3.1 Bayesian Networks 35 3.2 Hidden Markov Models 39 3.3 Mixtures of Statistical Models 31 3.4 Layered Neural Networks 45 3.5 Boltzmann Machines 50 4. The Reduced Rank Regression 53 4.1 The case when M=N=H and r= 0 54 4.2 Other cases 58 5. Determinantal Variety 62 | - |
dc.format | application/pdf | - |
dc.format.extent | 3479007 bytes | - |
dc.format.medium | application/pdf | - |
dc.language.iso | en | - |
dc.publisher | 서울대학교 대학원 | - |
dc.subject | Statistical Learning Theory | - |
dc.subject | Resolution of Singularities | - |
dc.subject.ddc | 510 | - |
dc.title | A Viewpoint of Algebraic Geometry in Singular Learning Theory | - |
dc.title.alternative | 대수기하학적 관점에서의 특이학습이론 | - |
dc.type | Thesis | - |
dc.description.degree | Master | - |
dc.contributor.affiliation | 자연과학대학 수리과학부 | - |
dc.date.awarded | 2018-02 | - |
- Appears in Collections:
- Files in This Item:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.