Skip to Main Content
 

Global Search Box

 
 
 

ETD Abstract Container

Abstract Header

Hierarchical Auto-Associative Polynomial Convolutional Neural Networks

Martell, Patrick Keith
http://rave.ohiolink.edu/etdc/view?acc_num=dayton1513164029518038

Abstract Details

2017, Master of Science (M.S.), University of Dayton, Electrical Engineering.
Convolutional neural networks (CNNs) lack ample methods to improve performance without either adding more input data, modifying existing data, or changing network design. This work seeks to add to the methods available that do not require more data or a trial and error approach to network design. This thesis seeks to demonstrate that a polynomial layer inserted into a CNN, compared to all other factors being equal has great potential to improve classification rates. There are some methods that seek to help fill the gap that this research also investigates an alternative solution. Most other methods in the similar problem space look at ways to improve performance of existing layers, such as modifying the type of pooling or activation functions. Also, methods discussed later, Dropout and DropConnect zero out nodes or connections, respectively, seeking to improve performance. This research focused on adding a new type of layer to typical CNNs, the polynomial layer. This layer adds a local connectivity to each of the perceptrons creating N connections up to the Nth power of the initial value of the perceptron. This is done in either the convolutional portion or the fully connected portion, with the idea that the higher dimensionality allows for better description of the input space. This idea was tested on two datasets, MNIST and CIFAR10, both classification databases with 10 classes. These datasets contain 28×28 grayscale and 32×32 RGB images, respectively. It was determined that the polynomial layer universally enabled the tested CNN to perform better on the MNIST data and the convolutional layer polynomials aid CNNs that are trained at a lower learning rate on the CIFAR10 dataset. Looking forward, more CNN designs should be analyzed, along with more learning rates, including ones with a variable rate. Additionally, performing tests on a wider range of datasets would also enable a broader understanding.
Vijayan Asari, Ph.D. (Advisor)
Theus Aspiras, PH.D. (Committee Member)
Eric Balster, Ph.D. (Committee Member)
53 p.
Electrical Engineering
Convolutional Neural Network; Polynomial; CNN; Classification; MNIST

Recommended Citations

Citations

  • Martell, P. K. (2017). Hierarchical Auto-Associative Polynomial Convolutional Neural Networks [Master's thesis, University of Dayton]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1513164029518038

    APA Style (7th edition)

  • Martell, Patrick. Hierarchical Auto-Associative Polynomial Convolutional Neural Networks. 2017. University of Dayton, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=dayton1513164029518038.

    MLA Style (8th edition)

  • Martell, Patrick. "Hierarchical Auto-Associative Polynomial Convolutional Neural Networks." Master's thesis, University of Dayton, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1513164029518038

    Chicago Manual of Style (17th edition)

dayton1513164029518038
461
© 2017, all rights reserved.
This open access ETD is published by University of Dayton and OhioLINK.