Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


wright1253572204.pdf (21.41 MB)

ETD Abstract Container

Abstract Header

A Study of Hardware Efficient Recombination Variants in a Mini Population Genetic Algorithm

Bhupathiraju Venkata, Shiva Satya Ramesh Varma
http://rave.ohiolink.edu/etdc/view?acc_num=wright1253572204

Abstract Details

2009, Master of Science in Computer Engineering (MSCE), Wright State University, Computer Engineering.
Evolvable Hardware is an emerging sub-field of evolutionary computation in which evolutionary algorithms are employed to create designs for hardware devices. Recent work has combined continuous time recurrent neural networks with the Mini Population (Minipop) Evolutionary Algorithm to create self-configuring device controllers. Standard Minipop eschews recombination operators due to the belief that they increase the size of an algorithm’s on chip implementation without adding significant search power for finding neural network controllers. The focus of this thesis is to challenge that thinking by testing a number of hardware efficient recombination operators against two benchmark problems. We consider variants that recombine at neuron parameter and whole neuron boundaries taking advantage of easily measured neuron output correlation information. Although we conclude that there is no compelling evidence to adopt any of these variants at this time, we have identified interesting opportunities that might be exploited in the future to improve Minipop search over spaces of neurodynamic systems
John Gallagher, PhD (Advisor)
John Gallagher, PhD (Committee Chair)
Mateen Rizki, PhD (Committee Member)
Michael Raymer, PhD (Committee Member)
94 p.
Computer Science
Minipop; IRU; WKH; euron; DQG; LQ; RI

Recommended Citations

Citations

  • Bhupathiraju Venkata, S. S. R. V. (2009). A Study of Hardware Efficient Recombination Variants in a Mini Population Genetic Algorithm [Master's thesis, Wright State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=wright1253572204

    APA Style (7th edition)

  • Bhupathiraju Venkata, Shiva Satya. A Study of Hardware Efficient Recombination Variants in a Mini Population Genetic Algorithm. 2009. Wright State University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=wright1253572204.

    MLA Style (8th edition)

  • Bhupathiraju Venkata, Shiva Satya. "A Study of Hardware Efficient Recombination Variants in a Mini Population Genetic Algorithm." Master's thesis, Wright State University, 2009. http://rave.ohiolink.edu/etdc/view?acc_num=wright1253572204

    Chicago Manual of Style (17th edition)

wright1253572204
375
© 2009, all rights reserved.
This open access ETD is published by Wright State University and OhioLINK.