본문

서브메뉴

Topics in Artificial Intelligence
Topics in Artificial Intelligence
Topics in Artificial Intelligence

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152139
ISBN  
9798384019435
DDC  
658
저자명  
Trevino Gavito, Andrea.
서명/저자  
Topics in Artificial Intelligence
발행사항  
[Sl] : Northwestern University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
102 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-02, Section: B.
주기사항  
Advisor: Klabjan, Diego.
학위논문주기  
Thesis (Ph.D.)--Northwestern University, 2024.
초록/해제  
요약Artificial intelligence (AI) is as a collective term that encompasses various technologies such as machine learning, deep learning, computer vision, and natural language processing, among others. It refers to the capability of computer systems to perform tasks traditionally demanding human intellect and continues to be a vigorously evolving field of research and ongoing advancement. As we navigate through the era of big data, the remarkable advancements in computing power have unlocked new horizons for AI, enabling it to integrate into various aspects of our daily lives, drive innovation and redefine the boundaries of what is possible.AI has become a foundational element in fields ranging from healthcare and finance to manufacturing, education, and transportation, demonstrating its potential impact across diverse sectors and its remarkable adaptability. This versatility has been propelled as AI has advanced its proficiency in processing a wider range of data types, such as images, text, video, and tabular datasets. With this exponential growth and integration into critical decision-making processes, the importance of understanding the rationale behind AI's decisions has also become crucial for building trust and ensuring ethical outcomes. This dissertation consists of three chapters, each of which delves into a distinct topic within the realm of AI, 1) Unsupervised Echocardiogram View Detection via Autoencoder-based Representation Learning, 2) Gradient-boosted Based Structured and Unstructured Learning, and 3) Multi-Layer Attention-Based Explainability via Transformers for Tabular Data.In the first chapter, we focus on a healthcare application and introduce a fully unsupervised echocardiographic view detection framework. It leverages convolutional autoencoders to obtain lower dimensional representations and the K-means algorithm for clustering them into view-related groups. Our approach focuses on discriminative patches from echocardiographic frames. Additionally, we propose a trainable inverse average layer to optimize decoding of average operations. By integrating both public and proprietary datasets, we demonstrate that significant improvements in model performance can be achieved when supplementing proprietary datasets with additional data sources.The second chapter delves into the intricacies of handling multi-modal data. We propose two frameworks to deal with problem settings in which both structured1 and unstructured data are available. Historically, structured data problems are best solved by traditional machine learning models such as boosting and tree-based algorithms, whereas deep learning has been widely applied to problems dealing with images, text, audio, and other unstructured data sources. For the setting in which structured and unstructured data are be available, our proposed frameworks allows joint learning on both data types by integrating the paradigms of boosting models and deep neural networks.The first framework, the boosted-feature-vector deep learning network, learns features from the structured data using gradient boosting and combines them with embeddings from unstructured data via a two-branch deep neural network. The second framework, the two-weak-learner boosting framework, extends the boosting paradigm to the setting with two input data sources. We present and compare first- and second-order methods of this framework.In the third chapter, model explainability is the main emphasis. We propose a graph-oriented attention-based explainability method for tabular data. A transformer architecture for tabular data, which is amenable to explainability, is considered. A novel method to leverage self-attention mechanism to provide explanations by taking into account the attention matrices of all heads and layers as a whole is introduced. The matrices are mapped to a graph structure where groups of features correspond to nodes and attention values to arcs. By finding the maximum probability paths in the graph, we identify groups of features providing larger contributions to explain the model's predictions. To assess the quality of multi-layer attention-based explanations, we compare them with popular attention-, gradient-, and perturbation-based explainability methods.
일반주제명  
Industrial engineering
일반주제명  
Computer science
일반주제명  
Medical imaging
일반주제명  
Information technology
키워드  
Machine learning
키워드  
Deep learning
키워드  
Natural language processing
키워드  
Echocardiograms
키워드  
Unstructured learning
기타저자  
Northwestern University Industrial Engineering and Management Sciences
기본자료저록  
Dissertations Abstracts International. 86-02B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017163135
■00520250211152139
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798384019435
■035    ▼a(MiAaPQ)AAI31484544
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a658
■1001  ▼aTrevino  Gavito,  Andrea.
■24510▼aTopics  in  Artificial  Intelligence
■260    ▼a[Sl]▼bNorthwestern  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a102  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-02,  Section:  B.
■500    ▼aAdvisor:  Klabjan,  Diego.
■5021  ▼aThesis  (Ph.D.)--Northwestern  University,  2024.
■520    ▼aArtificial  intelligence  (AI)  is  as  a  collective  term  that  encompasses  various  technologies  such  as  machine  learning,  deep  learning,  computer  vision,  and  natural  language  processing,  among  others.  It  refers  to  the  capability  of  computer  systems  to  perform  tasks  traditionally  demanding  human  intellect  and  continues  to  be  a  vigorously  evolving  field  of  research  and  ongoing  advancement.  As  we  navigate  through  the  era  of  big  data,  the  remarkable  advancements  in  computing  power  have  unlocked  new  horizons  for  AI,  enabling  it  to  integrate  into  various  aspects  of  our  daily  lives,  drive  innovation  and  redefine  the  boundaries  of  what  is  possible.AI  has  become  a  foundational  element  in  fields  ranging  from  healthcare  and  finance  to  manufacturing,  education,  and  transportation,  demonstrating  its  potential  impact  across  diverse  sectors  and  its  remarkable  adaptability.  This  versatility  has  been  propelled  as  AI  has  advanced  its  proficiency  in  processing  a  wider  range  of  data  types,  such  as  images,  text,  video,  and  tabular  datasets.  With  this  exponential  growth  and  integration  into  critical  decision-making  processes,  the  importance  of  understanding  the  rationale  behind  AI's  decisions  has  also  become  crucial  for  building  trust  and  ensuring  ethical  outcomes.  This  dissertation  consists  of  three  chapters,  each  of  which  delves  into  a  distinct  topic  within  the  realm  of  AI,  1)  Unsupervised  Echocardiogram  View  Detection  via  Autoencoder-based  Representation  Learning,  2)  Gradient-boosted  Based  Structured  and  Unstructured  Learning,  and  3)  Multi-Layer  Attention-Based  Explainability  via  Transformers  for  Tabular  Data.In  the  first  chapter,  we  focus  on  a  healthcare  application  and  introduce  a  fully  unsupervised  echocardiographic  view  detection  framework.  It  leverages  convolutional  autoencoders  to  obtain  lower  dimensional  representations  and  the  K-means  algorithm  for  clustering  them  into  view-related  groups.  Our  approach  focuses  on  discriminative  patches  from  echocardiographic  frames.  Additionally,  we  propose  a  trainable  inverse  average  layer  to  optimize  decoding  of  average  operations.  By  integrating  both  public  and  proprietary  datasets,  we  demonstrate  that  significant  improvements  in  model  performance  can  be  achieved  when  supplementing  proprietary  datasets  with  additional  data  sources.The  second  chapter  delves  into  the  intricacies  of  handling  multi-modal  data.  We  propose  two  frameworks  to  deal  with  problem  settings  in  which  both  structured1  and  unstructured  data  are  available.  Historically,  structured  data  problems  are  best  solved  by  traditional  machine  learning  models  such  as  boosting  and  tree-based  algorithms,  whereas  deep  learning  has  been  widely  applied  to  problems  dealing  with  images,  text,  audio,  and  other  unstructured  data  sources.  For  the  setting  in  which  structured  and  unstructured  data  are  be  available,  our  proposed  frameworks  allows  joint  learning  on  both  data  types  by  integrating  the  paradigms  of  boosting  models  and  deep  neural  networks.The  first  framework,  the  boosted-feature-vector  deep  learning  network,  learns  features  from  the  structured  data  using  gradient  boosting  and  combines  them  with  embeddings  from  unstructured  data  via  a  two-branch  deep  neural  network.  The  second  framework,  the  two-weak-learner  boosting  framework,  extends  the  boosting  paradigm  to  the  setting  with  two  input  data  sources.  We  present  and  compare  first-  and  second-order  methods  of  this  framework.In  the  third  chapter,  model  explainability  is  the  main  emphasis.  We  propose  a  graph-oriented  attention-based  explainability  method  for  tabular  data.  A  transformer  architecture  for  tabular  data,  which  is  amenable  to  explainability,  is  considered.  A  novel  method  to  leverage  self-attention  mechanism  to  provide  explanations  by  taking  into  account  the  attention  matrices  of  all  heads  and  layers  as  a  whole  is  introduced.  The  matrices  are  mapped  to  a  graph  structure  where  groups  of  features  correspond  to  nodes  and  attention  values  to  arcs.  By  finding  the  maximum  probability  paths  in  the  graph,  we  identify  groups  of  features  providing  larger  contributions  to  explain  the  model's  predictions.  To  assess  the  quality  of  multi-layer  attention-based  explanations,  we  compare  them  with  popular  attention-,  gradient-,  and  perturbation-based  explainability  methods.
■590    ▼aSchool  code:  0163.
■650  4▼aIndustrial  engineering
■650  4▼aComputer  science
■650  4▼aMedical  imaging
■650  4▼aInformation  technology
■653    ▼aMachine  learning
■653    ▼aDeep  learning
■653    ▼aNatural  language  processing
■653    ▼aEchocardiograms
■653    ▼aUnstructured  learning
■690    ▼a0546
■690    ▼a0800
■690    ▼a0984
■690    ▼a0489
■690    ▼a0574
■71020▼aNorthwestern  University▼bIndustrial  Engineering  and  Management  Sciences.
■7730  ▼tDissertations  Abstracts  International▼g86-02B.
■790    ▼a0163
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163135▼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
    TF11573 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.