서브메뉴
검색
Beyond the Black Box: Optimization Within Latent Spaces
Beyond the Black Box: Optimization Within Latent Spaces
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211152716
- ISBN
- 9798384053736
- DDC
- 004
- 저자명
- Kishore, Varsha.
- 서명/저자
- Beyond the Black Box: Optimization Within Latent Spaces
- 발행사항
- [Sl] : Cornell University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 193 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-03, Section: B.
- 주기사항
- Advisor: Weinberger, Kilian.
- 학위논문주기
- Thesis (Ph.D.)--Cornell University, 2024.
- 초록/해제
- 요약In the past decade, neural networks have evolved into extraordinarily powerful tools, with wide-ranging applications across many different domains. These models allow us to use immense computational power to learn low-level features and high-level abstract concepts from vast datasets.Neural networks embed data of different forms (text, image, audio, etc.) into high dimensional latent spaces that encode salient features of the data and capture complex relationships between data points. This thesis aims to probe model parameters and latent spaces-to understand not only how information is stored and processed in networks but also how the encoded knowledge can be extracted and harnessed. We leverage these insights to develop novel methods that optimize specific parameters or representations from trained models to perform various downstream tasks. We present three specific methods in this thesis. First, we introduce BERTScore, an algorithm that utilizes representations from pre-trained language models to measure the similarity between two pieces of text. BERTScore approximates a form of transport distance to match tokens in the texts. Then, we focus on an information retrieval setting, where transformers are trained end-to-end to map search queries to corresponding documents. In this setting, we introduce IncDSI, a method to add new documents to a trained retrieval system by solving a constrained convex optimization problem to obtain new document representations. Finally, we present Fixed Neural Network Steganography (FNNS), a technique for image steganography that hides information by exploiting a neural network's sensitivity to imperceptible perturbations.
- 일반주제명
- Computer science
- 일반주제명
- Computer engineering
- 일반주제명
- Systems science
- 일반주제명
- Information technology
- 키워드
- BERTScore
- 키워드
- Neural networks
- 키워드
- Data points
- 기타저자
- Cornell University Computer Science
- 기본자료저록
- Dissertations Abstracts International. 86-03B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017163503
■00520250211152716
■006m o d
■007cr#unu||||||||
■020 ▼a9798384053736
■035 ▼a(MiAaPQ)AAI31489136
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aKishore, Varsha.▼0(orcid)0009-0005-9392-3780
■24510▼aBeyond the Black Box: Optimization Within Latent Spaces
■260 ▼a[Sl]▼bCornell University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a193 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-03, Section: B.
■500 ▼aAdvisor: Weinberger, Kilian.
■5021 ▼aThesis (Ph.D.)--Cornell University, 2024.
■520 ▼aIn the past decade, neural networks have evolved into extraordinarily powerful tools, with wide-ranging applications across many different domains. These models allow us to use immense computational power to learn low-level features and high-level abstract concepts from vast datasets.Neural networks embed data of different forms (text, image, audio, etc.) into high dimensional latent spaces that encode salient features of the data and capture complex relationships between data points. This thesis aims to probe model parameters and latent spaces-to understand not only how information is stored and processed in networks but also how the encoded knowledge can be extracted and harnessed. We leverage these insights to develop novel methods that optimize specific parameters or representations from trained models to perform various downstream tasks. We present three specific methods in this thesis. First, we introduce BERTScore, an algorithm that utilizes representations from pre-trained language models to measure the similarity between two pieces of text. BERTScore approximates a form of transport distance to match tokens in the texts. Then, we focus on an information retrieval setting, where transformers are trained end-to-end to map search queries to corresponding documents. In this setting, we introduce IncDSI, a method to add new documents to a trained retrieval system by solving a constrained convex optimization problem to obtain new document representations. Finally, we present Fixed Neural Network Steganography (FNNS), a technique for image steganography that hides information by exploiting a neural network's sensitivity to imperceptible perturbations.
■590 ▼aSchool code: 0058.
■650 4▼aComputer science
■650 4▼aComputer engineering
■650 4▼aSystems science
■650 4▼aInformation technology
■653 ▼aBERTScore
■653 ▼aFixed Neural Network Steganography
■653 ▼aImage steganography
■653 ▼aNeural networks
■653 ▼aData points
■690 ▼a0984
■690 ▼a0489
■690 ▼a0464
■690 ▼a0790
■71020▼aCornell University▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g86-03B.
■790 ▼a0058
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163503▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
