Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


38180.pdf (1.85 MB)

ETD Abstract Container

Abstract Header

Abstractive Representation Modeling for Image Classification

Li, Xin
http://orcid.org/0000-0002-1584-7947
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1623250959448677

Abstract Details

2021, MS, University of Cincinnati, Engineering and Applied Science: Computer Science.
In recent years, artificial intelligence has achieved remarkable progress by showing its applicable values in various industries. Convolutional neural networks (CNN) and their derivative approaches are well known for their robustness and accuracy in handling visual data. However, as a data-driven approach, CNN also has limitations. In exchange for good performance, CNN requires a large amount of training data and a heavy training process. The intricate neural network layer design also needs to be reconstructed and tuned by experienced researchers for different problems. Finally, the “curse of Blackbox” is a well-known disadvantage of the neural network, preventing CNN from providing a reasonable explanation for the prediction results. All the above limitations remind us that the most cutting-edge approach is still in the state of weak AI. This thesis proposes an approach called Abstractive Representation Model (ARM), which is different from the traditional data-driven approaches. This goal of experimenting with such a model is to address CNN’s weaknesses and possibly develop a new way of handling image data.
Anca Ralescu, Ph.D. (Committee Chair)
Kenneth Berman, Ph.D. (Committee Member)
Kelly Cohen, Ph.D. (Committee Member)
Manish Kumar, Ph.D. (Committee Member)
Anoop Sathyan, PhD (Committee Member)
43 p.
Artificial Intelligence
Image Classification; Explainability; Convolutional Neural Network; Abstraction; K-Means Clustering

Recommended Citations

Citations

  • Li, X. (2021). Abstractive Representation Modeling for Image Classification [Master's thesis, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1623250959448677

    APA Style (7th edition)

  • Li, Xin. Abstractive Representation Modeling for Image Classification. 2021. University of Cincinnati, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ucin1623250959448677.

    MLA Style (8th edition)

  • Li, Xin. "Abstractive Representation Modeling for Image Classification." Master's thesis, University of Cincinnati, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1623250959448677

    Chicago Manual of Style (17th edition)

ucin1623250959448677
97
© 2021, all rights reserved.
This open access ETD is published by University of Cincinnati and OhioLINK.