본문

서브메뉴

Deep Learning With Estimation and Complexity Guarantees for Signal Processing
Deep Learning With Estimation and Complexity Guarantees for Signal Processing
Deep Learning With Estimation and Complexity Guarantees for Signal Processing

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152037
ISBN  
9798384479451
DDC  
621.3
저자명  
Chen, Kuan-Lin.
서명/저자  
Deep Learning With Estimation and Complexity Guarantees for Signal Processing
발행사항  
[Sl] : University of California, San Diego, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
173 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-04, Section: B.
주기사항  
Advisor: Rao, Bhaskar D.
학위논문주기  
Thesis (Ph.D.)--University of California, San Diego, 2024.
초록/해제  
요약This dissertation presents advancements in both the theory and applications of deep learning. The objectives include reducing complexity, enhancing interpretability, and offering superior methodologies for solving signal processing problems.On the theoretical side, we develop two major advances: one for complexity and another for interpretability. For complexity, we establish tighter upper bounds for the number of computational units required for a rectified linear unit (ReLU) neural network to represent or compute any given continuous piecewise linear (CPWL) function. Specifically, we prove that any CPWL function can be represented by a ReLU network whose number of hidden neurons is at most a quadratic function of the number of pieces of the CPWL function. This quadratic bound is independent of the input dimension and outperforms previous bounds exponentially, holding the state-of-the-art in the literature. When the number of linear components is also known, this bound reduces to a bilinear bound. On the other hand, a new upper bound on the number of pieces in terms of the number of linear components is proved, enabling different descriptions of neural complexity. In addition to existence, a polynomial-time algorithm is developed to identify a neural network that satisfies these tighter bounds, shedding light on reverse-engineering and network pruning. For interpretability, we prove that, the most popular building block in deep learning, the skip connection, can guarantee to improve representations over residual blocks when the expansion layer is sufficiently large. Its implications explain (a) why the residual network (ResNet) can avoid the degradation problem and be scaled to thousands of layers, (b) why the wide ResNet is superior than the ResNet, and (c) why the bottleneck blocks are more economical than the basic block. We design a simplified architecture called the residual nonlinear estimator (ResNEst) and propose a new architecture called the augmented ResNEst to develop guarantees for the ResNet. Under mild assumptions, it is proved that every local minimizer in the ResNEst can be a global minimizer, despite the nonconvex optimization landscape, implying that any local minimizer can be provably better than the best linear predictor.On the application side, we develop a new deep learning-based methodology, subspace representation learning, for the classic direction-of-arrival (DoA) estimation problem in array processing. The codomain of a deep learning model is defined as a union of Grassmannians reflecting signal subspaces of different dimensions. A family of distance functions on Grassmannians is proposed. In particular, we use geodesic distances to train a model and prove that it is possible for a ReLU network to approximate signal subspaces. Because a subspace is invariant to the selection of its bases, our methodology enlarges the solution space of a model compared to existing approaches learning covariance matrices. Furthermore, due to its geometry-agnostic nature, our methodology is robust to array imperfections. Numerical results show that subspace representation learning significantly outperforms existing semidefinite programming-based and deep learning-based covariance matrix reconstruction approaches for a wide range of scenarios.
일반주제명  
Electrical engineering
일반주제명  
Computer science
키워드  
Array processing
키워드  
Complexity
키워드  
Deep learning
키워드  
Machine learning
키워드  
Neural networks
키워드  
Signal processing
기타저자  
University of California, San Diego Electrical and Computer Engineering
기본자료저록  
Dissertations Abstracts International. 86-04B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017162645
■00520250211152037
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384479451
■035    ▼a(MiAaPQ)AAI31335643
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621.3
■1001  ▼aChen,  Kuan-Lin.
■24510▼aDeep  Learning  With  Estimation  and  Complexity  Guarantees  for  Signal  Processing
■260    ▼a[Sl]▼bUniversity  of  California,  San  Diego▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a173  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-04,  Section:  B.
■500    ▼aAdvisor:  Rao,  Bhaskar  D.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  San  Diego,  2024.
■520    ▼aThis  dissertation  presents  advancements  in  both  the  theory  and  applications  of  deep  learning.  The  objectives  include  reducing  complexity,  enhancing  interpretability,  and  offering  superior  methodologies  for  solving  signal  processing  problems.On  the  theoretical  side,  we  develop  two  major  advances:  one  for  complexity  and  another  for  interpretability.  For  complexity,  we  establish  tighter  upper  bounds  for  the  number  of  computational  units  required  for  a  rectified  linear  unit  (ReLU)  neural  network  to  represent  or  compute  any  given  continuous  piecewise  linear  (CPWL)  function.  Specifically,  we  prove  that  any  CPWL  function  can  be  represented  by  a  ReLU  network  whose  number  of  hidden  neurons  is  at  most  a  quadratic  function  of  the  number  of  pieces  of  the  CPWL  function.  This  quadratic  bound  is  independent  of  the  input  dimension  and  outperforms  previous  bounds  exponentially,  holding  the  state-of-the-art  in  the  literature.  When  the  number  of  linear  components  is  also  known,  this  bound  reduces  to  a  bilinear  bound.  On  the  other  hand,  a  new  upper  bound  on  the  number  of  pieces  in  terms  of  the  number  of  linear  components  is  proved,  enabling  different  descriptions  of  neural  complexity.  In  addition  to  existence,  a  polynomial-time  algorithm  is  developed  to  identify  a  neural  network  that  satisfies  these  tighter  bounds,  shedding  light  on  reverse-engineering  and  network  pruning.  For  interpretability,  we  prove  that,  the  most  popular  building  block  in  deep  learning,  the  skip  connection,  can  guarantee  to  improve  representations  over  residual  blocks  when  the  expansion  layer  is  sufficiently  large.  Its  implications  explain  (a)  why  the  residual  network  (ResNet)  can  avoid  the  degradation  problem  and  be  scaled  to  thousands  of  layers,  (b)  why  the  wide  ResNet  is  superior  than  the  ResNet,  and  (c)  why  the  bottleneck  blocks  are  more  economical  than  the  basic  block.  We  design  a  simplified  architecture  called  the  residual  nonlinear  estimator  (ResNEst)  and  propose  a  new  architecture  called  the  augmented  ResNEst  to  develop  guarantees  for  the  ResNet.  Under  mild  assumptions,  it  is  proved  that  every  local  minimizer  in  the  ResNEst  can  be  a  global  minimizer,  despite  the  nonconvex  optimization  landscape,  implying  that  any  local  minimizer  can  be  provably  better  than  the  best  linear  predictor.On  the  application  side,  we  develop  a  new  deep  learning-based  methodology,  subspace  representation  learning,  for  the  classic  direction-of-arrival  (DoA)  estimation  problem  in  array  processing.  The  codomain  of  a  deep  learning  model  is  defined  as  a  union  of  Grassmannians  reflecting  signal  subspaces  of  different  dimensions.  A  family  of  distance  functions  on  Grassmannians  is  proposed.  In  particular,  we  use  geodesic  distances  to  train  a  model  and  prove  that  it  is  possible  for  a  ReLU  network  to  approximate  signal  subspaces.  Because  a  subspace  is  invariant  to  the  selection  of  its  bases,  our  methodology  enlarges  the  solution  space  of  a  model  compared  to  existing  approaches  learning  covariance  matrices.  Furthermore,  due  to  its  geometry-agnostic  nature,  our  methodology  is  robust  to  array  imperfections.  Numerical  results  show  that  subspace  representation  learning  significantly  outperforms  existing  semidefinite  programming-based  and  deep  learning-based  covariance  matrix  reconstruction  approaches  for  a  wide  range  of  scenarios.
■590    ▼aSchool  code:  0033.
■650  4▼aElectrical  engineering
■650  4▼aComputer  science
■653    ▼aArray  processing
■653    ▼aComplexity
■653    ▼aDeep  learning
■653    ▼aMachine  learning
■653    ▼aNeural  networks
■653    ▼aSignal  processing
■690    ▼a0544
■690    ▼a0984
■690    ▼a0800
■71020▼aUniversity  of  California,  San  Diego▼bElectrical  and  Computer  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g86-04B.
■790    ▼a0033
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162645▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

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
    TF09944 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

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

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.