본문

서브메뉴

Interpretable Machine Learning Architectures for Efficient Signal Detection with Applications to Gravitational Wave Astronomy- [electronic resource]
Interpretable Machine Learning Architectures for Efficient Signal Detection with Applicati...
Interpretable Machine Learning Architectures for Efficient Signal Detection with Applications to Gravitational Wave Astronomy- [electronic resource]

상세정보

자료유형  
 학위논문파일 국외
최종처리일시  
20240214101923
ISBN  
9798380846783
DDC  
621.3
저자명  
Yan, Jingkai.
서명/저자  
Interpretable Machine Learning Architectures for Efficient Signal Detection with Applications to Gravitational Wave Astronomy - [electronic resource]
발행사항  
[S.l.]: : Columbia University., 2024
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2024
형태사항  
1 online resource(132 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 85-05, Section: B.
주기사항  
Advisor: Wright, John.
학위논문주기  
Thesis (Ph.D.)--Columbia University, 2024.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약Deep learning has seen rapid evolution in the past decade, accomplishing tasks that were previously unimaginable. At the same time, researchers strive to better understand and interpret the underlying mechanisms of the deep models, which are often justifiably regarded as "black boxes". Overcoming this deficiency will not only serve to suggest better learning architectures and training methods, but also extend deep learning to scenarios where interpretability is key to the application. One such scenario is signal detection and estimation, with gravitational wave detection as a specific example, where classic methods are often preferred for their interpretability. Nonetheless, while classic statistical detection methods such as matched filtering excel in their simplicity and intuitiveness, they can be suboptimal in terms of both accuracy and computational efficiency. Therefore, it is appealing to have methods that achieve "the best of both worlds", namely enjoying simultaneously excellent performance and interpretability.In this thesis, we aim to bridge this gap between modern deep learning and classic statistical detection, by revisiting the signal detection problem from a new perspective. First, to address the perceived distinction in interpretability between classic matched filtering and deep learning, we state the intrinsic connections between the two families of methods, and identify how trainable networks can address the structural limitations of matched filtering. Based on these ideas, we propose two trainable architectures that are constructed based on matched filtering, but with learnable templates and adaptivity to unknown noise distributions, and therefore higher detection accuracy. We next turn our attention toward improving the computational efficiency of detection, where we aim to design architectures that leverage structures within the problem for efficiency gains. By leveraging the statistical structure of class imbalance, we integrate hierarchical detection into trainable networks, and use a novel loss function which explicitly encodes both detection accuracy and efficiency. Furthermore, by leveraging the geometric structure of the signal set, we consider using signal space optimization as an alternative computational primitive for detection, which is intuitively more efficient than covering with a template bank. We theoretical prove the efficiency gain by analyzing Riemannian gradient descent on the signal manifold, which reveals an exponential improvement in efficiency over matched filtering. We also propose a practical trainable architecture for template optimization, which makes use of signal embedding and kernel interpolation.We demonstrate the performance of all proposed architectures on the task of gravitational wave detection in astrophysics, where matched filtering is the current method of choice. The architectures are also widely applicable to general signal or pattern detection tasks, which we exemplify with the handwritten digit recognition task using the template optimization architecture. Together, we hope the this work useful to scientists and engineers seeking machine learning architectures with high performance and interpretability, and contribute to our understanding of deep learning as a whole.
일반주제명  
Electrical engineering.
일반주제명  
Computer science.
키워드  
Gravitational wave detection
키워드  
Interpretability
키워드  
Machine learning
키워드  
Optimization
키워드  
Signal detection
기타저자  
Columbia University Electrical Engineering
기본자료저록  
Dissertations Abstracts International. 85-05B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2024      us  |||||||||||||||c||eng  d
■001000016935358
■00520240214101923
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798380846783
■035    ▼a(MiAaPQ)AAI30691386
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621.3
■1001  ▼aYan,  Jingkai.
■24510▼aInterpretable  Machine  Learning  Architectures  for  Efficient  Signal  Detection  with  Applications  to  Gravitational  Wave  Astronomy▼h[electronic  resource]
■260    ▼a[S.l.]:▼bColumbia  University.  ▼c2024
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2024
■300    ▼a1  online  resource(132  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-05,  Section:  B.
■500    ▼aAdvisor:  Wright,  John.
■5021  ▼aThesis  (Ph.D.)--Columbia  University,  2024.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aDeep  learning  has  seen  rapid  evolution  in  the  past  decade,  accomplishing  tasks  that  were  previously  unimaginable.  At  the  same  time,  researchers  strive  to  better  understand  and  interpret  the  underlying  mechanisms  of  the  deep  models,  which  are  often  justifiably  regarded  as  "black  boxes".  Overcoming  this  deficiency  will  not  only  serve  to  suggest  better  learning  architectures  and  training  methods,  but  also  extend  deep  learning  to  scenarios  where  interpretability  is  key  to  the  application.  One  such  scenario  is  signal  detection  and  estimation,  with  gravitational  wave  detection  as  a  specific  example,  where  classic  methods  are  often  preferred  for  their  interpretability.  Nonetheless,  while  classic  statistical  detection  methods  such  as  matched  filtering  excel  in  their  simplicity  and  intuitiveness,  they  can  be  suboptimal  in  terms  of  both  accuracy  and  computational  efficiency.  Therefore,  it  is  appealing  to  have  methods  that  achieve  "the  best  of  both  worlds",  namely  enjoying  simultaneously  excellent  performance  and  interpretability.In  this  thesis,  we  aim  to  bridge  this  gap  between  modern  deep  learning  and  classic  statistical  detection,  by  revisiting  the  signal  detection  problem  from  a  new  perspective.  First,  to  address  the  perceived  distinction  in  interpretability  between  classic  matched  filtering  and  deep  learning,  we  state  the  intrinsic  connections  between  the  two  families  of  methods,  and  identify  how  trainable  networks  can  address  the  structural  limitations  of  matched  filtering.  Based  on  these  ideas,  we  propose  two  trainable  architectures  that  are  constructed  based  on  matched  filtering,  but  with  learnable  templates  and  adaptivity  to  unknown  noise  distributions,  and  therefore  higher  detection  accuracy.  We  next  turn  our  attention  toward  improving  the  computational  efficiency  of  detection,  where  we  aim  to  design  architectures  that  leverage  structures  within  the  problem  for  efficiency  gains.  By  leveraging  the  statistical  structure  of  class  imbalance,  we  integrate  hierarchical  detection  into  trainable  networks,  and  use  a  novel  loss  function  which  explicitly  encodes  both  detection  accuracy  and  efficiency.  Furthermore,  by  leveraging  the  geometric  structure  of  the  signal  set,  we  consider  using  signal  space  optimization  as  an  alternative  computational  primitive  for  detection,  which  is  intuitively  more  efficient  than  covering  with  a  template  bank.  We  theoretical  prove  the  efficiency  gain  by  analyzing  Riemannian  gradient  descent  on  the  signal  manifold,  which  reveals  an  exponential  improvement  in  efficiency  over  matched  filtering.  We  also  propose  a  practical  trainable  architecture  for  template  optimization,  which  makes  use  of  signal  embedding  and  kernel  interpolation.We  demonstrate  the  performance  of  all  proposed  architectures  on  the  task  of  gravitational  wave  detection  in  astrophysics,  where  matched  filtering  is  the  current  method  of  choice.  The  architectures  are  also  widely  applicable  to  general  signal  or  pattern  detection  tasks,  which  we  exemplify  with  the  handwritten  digit  recognition  task  using  the  template  optimization  architecture.  Together,  we  hope  the  this  work  useful  to  scientists  and  engineers  seeking  machine  learning  architectures  with  high  performance  and  interpretability,  and  contribute  to  our  understanding  of  deep  learning  as  a  whole.
■590    ▼aSchool  code:  0054.
■650  4▼aElectrical  engineering.
■650  4▼aComputer  science.
■653    ▼aGravitational  wave  detection
■653    ▼aInterpretability
■653    ▼aMachine  learning
■653    ▼aOptimization
■653    ▼aSignal  detection
■690    ▼a0544
■690    ▼a0984
■71020▼aColumbia  University▼bElectrical  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-05B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0054
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16935358▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.
■980    ▼a202402▼f2024

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF07222 전자도서 마이폴더 부재도서신고 비도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.