본문

서브메뉴

Design Approaches for Lightweight Machine Learning Models- [electronic resource]
Design Approaches for Lightweight Machine Learning Models - [electronic resource]
Design Approaches for Lightweight Machine Learning Models- [electronic resource]

상세정보

자료유형  
 학위논문파일 국외
최종처리일시  
20240214100116
ISBN  
9798379926724
DDC  
004
저자명  
Chang, Yangyang.
서명/저자  
Design Approaches for Lightweight Machine Learning Models - [electronic resource]
발행사항  
[S.l.]: : University of Minnesota., 2023
발행사항  
Ann Arbor : : ProQuest Dissertations & Theses,, 2023
형태사항  
1 online resource(131 p.)
주기사항  
Source: Dissertations Abstracts International, Volume: 85-01, Section: B.
주기사항  
Advisor: Sobelman, Gerald.
학위논문주기  
Thesis (Ph.D.)--University of Minnesota, 2023.
사용제한주기  
This item must not be sold to any third party vendors.
초록/해제  
요약In this era of data explosion, the diversity and complexity of data are gradually increasing. The corresponding data processing models become massive and complicated. Especially for dealing with high-dimensional data, large-size inputs, and low latency, modern machine learning methods (e.g., deep neural networks) require advanced hardware solutions (e.g., High Power Graphic Processing Units, Tensor Process Units). To run the models efficiently on embedded platforms, designs of lightweight machine learning are important to ensure small computation and memory requirements. This thesis shows six innovative designs of lightweight machine learning models. Specifically, the introduced designs include the quantized vision transformer, optimized binarized neural networks (BNNs), and lightweight convolutional neural networks (CNNs). For high- dimensional multitasking continuous and discrete optimizations, the innovative lightweight designs contain the modified multifactorial and cross-target evolutionary algorithms (EAs). For data compression, this thesis proposes a hybrid compressor for medical electrocardiogram (ECG) data on an embedded system. In future work, the overall lightweight design framework can be integrated by the proposed structures to include full-system compression, optimization, and quantization.Quantization using a small number of bits shows promise for reducing latency and memory usage in DNNs. However, most quantization methods cannot readily handle complicated functions such as exponential and square root, and prior approaches involve complex processes that must interact with floating-point calculations during the quantization pass. The proposed quantized vision transformer in this thesis provides a robust method for the full integer quantization of the vision transformer without requiring any intermediate floating-point computations. The quantization techniques can be applied in various hardware or software implementations, including processor/memory architectures and FPGAs.BNNs have shown promise in low-power embedded systems, but these are typically designed starting from existing architectures that are based on floating-point number representations. It is also hard to meet the classification requirements because the weights and activations are limited to ±1. This thesis applies the efficient genetic algorithm (GA) to optimize a fully connected binarized architecture to increase the BNN performance without changing its basic operators. The simulation results demonstrate the effectiveness of the proposed method to improve the performance of BNNs.Novel design frameworks for lightweight CNNs are proposed for embedded system applications on image classification tasks. Scalable lightweight architectures for CNNs are first proposed. The population-based metaheuristic approaches of the genetic algorithm (GA), cuckoo search (CS), multifactorial evolutionary algorithm (MFEA), and a proposed hybrid evolutionary approach are then used to optimize the proposed CNN architectures. The proposed optimization process uses no assumptions (e.g., weight-sharing) or approximations (e.g., surrogate function). Two encoding methods are proposed related to the most critical computational parts of CNNs, and the metaheuristic approaches are compared for small population sizes. The results from these various metaheuristic approaches are evaluated using the metrics of computation time and classification accuracy. The final architecture obtained, which has a favorable tradeoff between the amount of computation and accuracy, is indicated.On a set of large-dimensional, multitasking, continuous optimization problems, multifactorial optimization has become one of the most promising paradigms for evolutionary multitasking within the field of computational intelligence. This thesis presents an in-depth analysis of this approach by considering several variations of the standard MFEA. By using a simpler structure together with some enhanced operators, two new MFEAs are proposed. In the approach presented, redundant hyperparameters are removed and the operators are simplified. Compared with the traditional MFEA, the proposed two MFEAs produce better results and are suitable for an embedded system implementation.To handle both non-convex continuous and NP-hard discrete optimization problems, this thesis proposes the class algorithm, a new type of evolutionary algorithm. The methodology is inspired by the concepts of division of labor and specialization. Individuals form subpopulations of different classes, and each class has its own characteristics. The entire population evolves through influences among individuals within and between the different subpopulations. The performance of the class algorithm surpasses other evolutionary algorithms for many test functions of single-objective continuous optimization benchmark problems. Compared with mature application software, the class algorithm also shows a competent ability to solve large-scale discrete optimization problems. The computation time is only 0.48 or 0.36 of published GA results when the class algorithm run in series or parallel, respectively, and the class algorithm is very suitable for use either in embedded systems or on a traditional hardware platform. In summary, compared with traditional EAs, the class algorithm not only has better performance but also has a smaller runtime.Cardiovascular diseases are the number one cause of death worldwide. Monitoring patients with heart disease can be done by analyzing the electrocardiogram. However, the large amount of data poses a burden for a system that is implemented as an embedded system with limited memory and computation capabilities. Traditionally, lossless compression methods have been favored to reduce the memory requirements due to the critical nature of the application. However, if the reconstruction of a lossy signal does not significantly affect the diagnosis capability, then those methods may become attractive due to their larger compression ratios. This thesis proposes a hybrid lossy/lossless compression system with good signal fidelity and compression ratio characteristics. The performance is evaluated after decompression using deep neural networks (DNNs) that have been shown to have good classification capabilities. For the CODE (Clinical Outcomes in Digital Electrocardiology) dataset, the proposed hybrid compressor can achieve an average compression ratio of 5.18 with a mean squared error of 0.20, and DNN-based diagnoses of the decompressed waveforms have, on average, only 0.8 additional erroneous diagnoses out of a total of 402 cases compared to using the original ECG data. For the PTB-XL dataset, the hybrid compressor can achieve a high average compression ratio of 4.91 with a mean squared error of 0.01. In addition, the decompressed ECGs have only a 2.46% lower macro averaged area under the receiver operating characteristic curve (AUC) score than when using the original ECGs.
일반주제명  
Computer science.
일반주제명  
Electrical engineering.
키워드  
Convolutional neural networks
키워드  
Evolutionary algorithm
키워드  
Medical electrocardiogram
키워드  
Network architecture
키워드  
Machine learning
기타저자  
University of Minnesota Electrical Engineering
기본자료저록  
Dissertations Abstracts International. 85-01B.
기본자료저록  
Dissertation Abstract International
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008240612s2023      us  |||||||||||||||c||eng  d
■001000016931780
■00520240214100116
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798379926724
■035    ▼a(MiAaPQ)AAI30423005
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aChang,  Yangyang.
■24510▼aDesign  Approaches  for  Lightweight  Machine  Learning  Models▼h[electronic  resource]
■260    ▼a[S.l.]:▼bUniversity  of  Minnesota.  ▼c2023
■260  1▼aAnn  Arbor  :▼bProQuest  Dissertations  &  Theses,  ▼c2023
■300    ▼a1  online  resource(131  p.)
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-01,  Section:  B.
■500    ▼aAdvisor:  Sobelman,  Gerald.
■5021  ▼aThesis  (Ph.D.)--University  of  Minnesota,  2023.
■506    ▼aThis  item  must  not  be  sold  to  any  third  party  vendors.
■520    ▼aIn  this  era  of  data  explosion,  the  diversity  and  complexity  of  data  are  gradually  increasing.  The  corresponding  data  processing  models  become  massive  and  complicated.  Especially  for  dealing  with  high-dimensional  data,  large-size  inputs,  and  low  latency,  modern  machine  learning  methods  (e.g.,  deep  neural  networks)  require  advanced  hardware  solutions  (e.g.,  High  Power  Graphic  Processing  Units,  Tensor  Process  Units).  To  run  the  models  efficiently  on  embedded  platforms,  designs  of  lightweight  machine  learning  are  important  to  ensure  small  computation  and  memory  requirements.  This  thesis  shows  six  innovative  designs  of  lightweight  machine  learning  models.  Specifically,  the  introduced  designs  include  the  quantized  vision  transformer,  optimized  binarized  neural  networks  (BNNs),  and  lightweight  convolutional  neural  networks  (CNNs).  For  high-  dimensional  multitasking  continuous  and  discrete  optimizations,  the  innovative  lightweight  designs  contain  the  modified  multifactorial  and  cross-target  evolutionary  algorithms  (EAs).  For  data  compression,  this  thesis  proposes  a  hybrid  compressor  for  medical  electrocardiogram  (ECG)  data  on  an  embedded  system.  In  future  work,  the  overall  lightweight  design  framework  can  be  integrated  by  the  proposed  structures  to  include  full-system  compression,  optimization,  and  quantization.Quantization  using  a  small  number  of  bits  shows  promise  for  reducing  latency  and  memory  usage  in  DNNs.  However,  most  quantization  methods  cannot  readily  handle  complicated  functions  such  as  exponential  and  square  root,  and  prior  approaches  involve  complex  processes  that  must  interact  with  floating-point  calculations  during  the  quantization  pass.  The  proposed  quantized  vision  transformer  in  this  thesis  provides  a  robust  method  for  the  full  integer  quantization  of  the  vision  transformer  without  requiring  any  intermediate  floating-point  computations.  The  quantization  techniques  can  be  applied  in  various  hardware  or  software  implementations,  including  processor/memory  architectures  and  FPGAs.BNNs  have  shown  promise  in  low-power  embedded  systems,  but  these  are  typically  designed  starting  from  existing  architectures  that  are  based  on  floating-point  number  representations.  It  is  also  hard  to  meet  the  classification  requirements  because  the  weights  and  activations  are  limited  to  ±1.  This  thesis  applies  the  efficient  genetic  algorithm  (GA)  to  optimize  a  fully  connected  binarized  architecture  to  increase  the  BNN  performance  without  changing  its  basic  operators.  The  simulation  results  demonstrate  the  effectiveness  of  the  proposed  method  to  improve  the  performance  of  BNNs.Novel  design  frameworks  for  lightweight  CNNs  are  proposed  for  embedded  system  applications  on  image  classification  tasks.  Scalable  lightweight  architectures  for  CNNs  are  first  proposed.  The  population-based  metaheuristic  approaches  of  the  genetic  algorithm  (GA),  cuckoo  search  (CS),  multifactorial  evolutionary  algorithm  (MFEA),  and  a  proposed  hybrid  evolutionary  approach  are  then  used  to  optimize  the  proposed  CNN  architectures.  The  proposed  optimization  process  uses  no  assumptions  (e.g.,  weight-sharing)  or  approximations  (e.g.,  surrogate  function).  Two  encoding  methods  are  proposed  related  to  the  most  critical  computational  parts  of  CNNs,  and  the  metaheuristic  approaches  are  compared  for  small  population  sizes.  The  results  from  these  various  metaheuristic  approaches  are  evaluated  using  the  metrics  of  computation  time  and  classification  accuracy.  The  final  architecture  obtained,  which  has  a  favorable  tradeoff  between  the  amount  of  computation  and  accuracy,  is  indicated.On  a  set  of  large-dimensional,  multitasking,  continuous  optimization  problems,  multifactorial  optimization  has  become  one  of  the  most  promising  paradigms  for  evolutionary  multitasking  within  the  field  of  computational  intelligence.  This  thesis  presents  an  in-depth  analysis  of  this  approach  by  considering  several  variations  of  the  standard  MFEA.  By  using  a  simpler  structure  together  with  some  enhanced  operators,  two  new  MFEAs  are  proposed.  In  the  approach  presented,  redundant  hyperparameters  are  removed  and  the  operators  are  simplified.  Compared  with  the  traditional  MFEA,  the  proposed  two  MFEAs  produce  better  results  and  are  suitable  for  an  embedded  system  implementation.To  handle  both  non-convex  continuous  and  NP-hard  discrete  optimization  problems,  this  thesis  proposes  the  class  algorithm,  a  new  type  of  evolutionary  algorithm.  The  methodology  is  inspired  by  the  concepts  of  division  of  labor  and  specialization.  Individuals  form  subpopulations  of  different  classes,  and  each  class  has  its  own  characteristics.  The  entire  population  evolves  through  influences  among  individuals  within  and  between  the  different  subpopulations.  The  performance  of  the  class  algorithm  surpasses  other  evolutionary  algorithms  for  many  test  functions  of  single-objective  continuous  optimization  benchmark  problems.  Compared  with  mature  application  software,  the  class  algorithm  also  shows  a  competent  ability  to  solve  large-scale  discrete  optimization  problems.  The  computation  time  is  only  0.48  or  0.36  of  published  GA  results  when  the  class  algorithm  run  in  series  or  parallel,  respectively,  and  the  class  algorithm  is  very  suitable  for  use  either  in  embedded  systems  or  on  a  traditional  hardware  platform.  In  summary,  compared  with  traditional  EAs,  the  class  algorithm  not  only  has  better  performance  but  also  has  a  smaller  runtime.Cardiovascular  diseases  are  the  number  one  cause  of  death  worldwide.  Monitoring  patients  with  heart  disease  can  be  done  by  analyzing  the  electrocardiogram.  However,  the  large  amount  of  data  poses  a  burden  for  a  system  that  is  implemented  as  an  embedded  system  with  limited  memory  and  computation  capabilities.  Traditionally,  lossless  compression  methods  have  been  favored  to  reduce  the  memory  requirements  due  to  the  critical  nature  of  the  application.  However,  if  the  reconstruction  of  a  lossy  signal  does  not  significantly  affect  the  diagnosis  capability,  then  those  methods  may  become  attractive  due  to  their  larger  compression  ratios.  This  thesis  proposes  a  hybrid  lossy/lossless  compression  system  with  good  signal  fidelity  and  compression  ratio  characteristics.  The  performance  is  evaluated  after  decompression  using  deep  neural  networks  (DNNs)  that  have  been  shown  to  have  good  classification  capabilities.  For  the  CODE  (Clinical  Outcomes  in  Digital  Electrocardiology)  dataset,  the  proposed  hybrid  compressor  can  achieve  an  average  compression  ratio  of  5.18  with  a  mean  squared  error  of  0.20,  and  DNN-based  diagnoses  of  the  decompressed  waveforms  have,  on  average,  only  0.8  additional  erroneous  diagnoses  out  of  a  total  of  402  cases  compared  to  using  the  original  ECG  data.  For  the  PTB-XL  dataset,  the  hybrid  compressor  can  achieve  a  high  average  compression  ratio  of  4.91  with  a  mean  squared  error  of  0.01.  In  addition,  the  decompressed  ECGs  have  only  a  2.46%  lower  macro  averaged  area  under  the  receiver  operating  characteristic  curve  (AUC)  score  than  when  using  the  original  ECGs.
■590    ▼aSchool  code:  0130.
■650  4▼aComputer  science.
■650  4▼aElectrical  engineering.
■653    ▼aConvolutional  neural  networks
■653    ▼aEvolutionary  algorithm
■653    ▼aMedical  electrocardiogram
■653    ▼aNetwork  architecture
■653    ▼aMachine  learning
■690    ▼a0800
■690    ▼a0984
■690    ▼a0544
■71020▼aUniversity  of  Minnesota▼bElectrical  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-01B.
■773    ▼tDissertation  Abstract  International
■790    ▼a0130
■791    ▼aPh.D.
■792    ▼a2023
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T16931780▼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
    TF05813 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.