서브메뉴
검색
Translating Between Scientific Computing and Machine Learning With Automatic Differentiation
Translating Between Scientific Computing and Machine Learning With Automatic Differentiation
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211152026
- ISBN
- 9798384463702
- DDC
- 004
- 저자명
- Oktay, Deniz.
- 서명/저자
- Translating Between Scientific Computing and Machine Learning With Automatic Differentiation
- 발행사항
- [Sl] : Princeton University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 105 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-04, Section: B.
- 주기사항
- Advisor: Adams, Ryan P.
- 학위논문주기
- Thesis (Ph.D.)--Princeton University, 2024.
- 초록/해제
- 요약Scientific computing and machine learning, although historically separate fields, have seen much effort in unification as of recent years, especially as machine learning techniques have shown promise in scientific problems. In this thesis, I present work in the intersection of these areas, using automatic differentiation (AD) as the common language between the two. First, I present a methodological advancement in AD: Randomized Automatic Differentiation, a technique to reduce the memory usage of AD, and show that it can provide memory improvements in both machine learning and scientific computing applications.Next, I focus on mechanical design. I first describe Varmint: A Variational Material Integrator, which is a robust simulator for the statics of large deformation elasticity, using automatic differentiation as a first class citizen. Building this simulator allows us easy interoperability between machine learning and solid mechanics problems, and has been used as in several published and in submission works. I will then describe Neuromechanical Autoencoders, where we coupled neural network controllers with mechanical metamaterials to create artificial mechanical intelligence. The neural network "encoder" consumes a representation of the task-in this case, achieving a particular deformation-and nonlinearly transforms this into a set of linear actuations which play the role of the latent encoding. These actuations then displace the boundaries of the mechanical metamaterial inducing another nonlinear transformation due to the complex learned geometry of the pores; the resulting deformation corresponds to the "decoder".
- 일반주제명
- Computer science
- 일반주제명
- Information technology
- 키워드
- Machine learning
- 키워드
- Neural networks
- 기타저자
- Princeton University Computer Science
- 기본자료저록
- Dissertations Abstracts International. 86-04B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017162558
■00520250211152026
■006m o d
■007cr#unu||||||||
■020 ▼a9798384463702
■035 ▼a(MiAaPQ)AAI31333303
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aOktay, Deniz.▼0(orcid)0000-0001-7104-0104
■24510▼aTranslating Between Scientific Computing and Machine Learning With Automatic Differentiation
■260 ▼a[Sl]▼bPrinceton University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a105 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-04, Section: B.
■500 ▼aAdvisor: Adams, Ryan P.
■5021 ▼aThesis (Ph.D.)--Princeton University, 2024.
■520 ▼aScientific computing and machine learning, although historically separate fields, have seen much effort in unification as of recent years, especially as machine learning techniques have shown promise in scientific problems. In this thesis, I present work in the intersection of these areas, using automatic differentiation (AD) as the common language between the two. First, I present a methodological advancement in AD: Randomized Automatic Differentiation, a technique to reduce the memory usage of AD, and show that it can provide memory improvements in both machine learning and scientific computing applications.Next, I focus on mechanical design. I first describe Varmint: A Variational Material Integrator, which is a robust simulator for the statics of large deformation elasticity, using automatic differentiation as a first class citizen. Building this simulator allows us easy interoperability between machine learning and solid mechanics problems, and has been used as in several published and in submission works. I will then describe Neuromechanical Autoencoders, where we coupled neural network controllers with mechanical metamaterials to create artificial mechanical intelligence. The neural network "encoder" consumes a representation of the task-in this case, achieving a particular deformation-and nonlinearly transforms this into a set of linear actuations which play the role of the latent encoding. These actuations then displace the boundaries of the mechanical metamaterial inducing another nonlinear transformation due to the complex learned geometry of the pores; the resulting deformation corresponds to the "decoder".
■590 ▼aSchool code: 0181.
■650 4▼aComputer science
■650 4▼aInformation technology
■653 ▼aScientific computing
■653 ▼aMachine learning
■653 ▼aAutomatic differentiation
■653 ▼aNeural networks
■653 ▼aMechanical metamaterials
■690 ▼a0984
■690 ▼a0800
■690 ▼a0489
■71020▼aPrinceton University▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g86-04B.
■790 ▼a0181
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162558▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
