Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


Brooke Weborg Thesis.pdf (18.52 MB)

ETD Abstract Container

Abstract Header

Reservoir Computing: Empirical Investigation into Sensitivity of Configuring Echo State Networks for Representative Benchmark Problem Domains

Weborg, Brooke Renee
http://orcid.org/0000-0002-1525-9686
http://rave.ohiolink.edu/etdc/view?acc_num=toledo1628252790883843

Abstract Details

2021, Master of Science, University of Toledo, Engineering (Computer Science).
This research examines Echo State Network, a reservoir computer, performance using four different benchmark problems, then proposes heuristics or rules of thumb for configuring the architecture, as well as the selection of parameters and their values, which are applicable to problems within the same domain, to help serve to fill the ‘experience gap’ needed by those entering this field of study. The influence of various parameter selections and their value adjustments, as well as architectural changes made to an Echo State Network, a powerful recurrent neural network configured as a reservoir computer, can be difficult to understand without experience in the field, and even some hyperparameter optimization algorithms may have difficulty adjusting parameter values without proper manual selections made first; therefore, it is imperative to understand the effects of parameters and their value selection on echo state network architecture performance for a successful build. Thus, to address the requirement for an extensive background in Echo State Network architecture, as well as examine how Echo State Network performance is affected with respect to variations in architecture, design, and parameter selection and values, a series of benchmark tasks representing different problem domains, including time series prediction, pattern generation, chaotic system prediction, and time series classification, were modeled and experimented on to show the impact on the performance of Echo State Network.
Gursel Serpen (Advisor)
Kevin Xu (Committee Member)
Joshua Stuckner (Committee Member)
Lawrence Thomas (Committee Member)
213 p.
Computer Engineering; Computer Science
Echo State Network; Echo State Networks; Recurrent Neural Network; Recurrent Neural Networks; Reservoir Computing; Reservoir Computer; Machine Learning; Time Series Classification; Time Series Prediction; Chaotic Time Series Prediction; Pattern Generation; Echo State Network Architecture; Echo State Network Parameters; Parameters; Architecture

Recommended Citations

Citations

  • Weborg, B. R. (2021). Reservoir Computing: Empirical Investigation into Sensitivity of Configuring Echo State Networks for Representative Benchmark Problem Domains [Master's thesis, University of Toledo]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1628252790883843

    APA Style (7th edition)

  • Weborg, Brooke. Reservoir Computing: Empirical Investigation into Sensitivity of Configuring Echo State Networks for Representative Benchmark Problem Domains. 2021. University of Toledo, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=toledo1628252790883843.

    MLA Style (8th edition)

  • Weborg, Brooke. "Reservoir Computing: Empirical Investigation into Sensitivity of Configuring Echo State Networks for Representative Benchmark Problem Domains." Master's thesis, University of Toledo, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1628252790883843

    Chicago Manual of Style (17th edition)

toledo1628252790883843
47
© 2021, all rights reserved.
This open access ETD is published by University of Toledo and OhioLINK.