Skip to Main Content
Frequently Asked Questions
Submit an ETD
Global Search Box
Need Help?
Keyword Search
Participating Institutions
Advanced Search
School Logo
Files
File List
case1056555044.pdf (2.6 MB)
ETD Abstract Container
Abstract Header
Silicon neural networks for optimization problems
Author Info
Cho, Yong Beom
Permalink:
http://rave.ohiolink.edu/etdc/view?acc_num=case1056555044
Abstract Details
Year and Degree
1992, Doctor of Philosophy, Case Western Reserve University, Electrical Engineering.
Abstract
This dissertation will present two aspects of artificial neural networks: some efficient parallel algorithms for assignment problems, and a silicon neural network architecture for optimization problems with details of a VLSI chip design. Assignment problems are a class of global optimization problems that pose a computational bottleneck in many real-time systems. The goal of the assignment problem is not only to satisfy a problem's natural constraints, but also to minimum the total cost of assignments. The difficulty of this problem lies in finding the global minimum instead of a local minimum. Some demonstrated applications for the assignment problem are: (1) weapon-target assignment problem; and (2) n-task-n-person problem. Although the study of elements within real neural systems is essential for the progress and understanding of system organization, it is still difficult to implement a nervous system in silicon. However, the rapid progress in VLSI technology has made it possible to fabricate a medium-sized neural system on a single silicon wafer. In this dissertation, three neural network VLSI chips are presented to solve three separate NP-complete optimization problems: A Hopfield-type conductance matrix for the planarization problem; a maximum neural network for the bipartite subgraph problem; and a hysteresis McCulloch-Pitts neuron for the 6 x 6 knight's tour problem.
Committee
Yoshiyasu Takefuji (Advisor)
Pages
104 p.
Keywords
Silicon neural networks optimization problems
Recommended Citations
Refworks
EndNote
RIS
Mendeley
Citations
Cho, Y. B. (1992).
Silicon neural networks for optimization problems
[Doctoral dissertation, Case Western Reserve University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=case1056555044
APA Style (7th edition)
Cho, Yong.
Silicon neural networks for optimization problems.
1992. Case Western Reserve University, Doctoral dissertation.
OhioLINK Electronic Theses and Dissertations Center
, http://rave.ohiolink.edu/etdc/view?acc_num=case1056555044.
MLA Style (8th edition)
Cho, Yong. "Silicon neural networks for optimization problems." Doctoral dissertation, Case Western Reserve University, 1992. http://rave.ohiolink.edu/etdc/view?acc_num=case1056555044
Chicago Manual of Style (17th edition)
Abstract Footer
Document number:
case1056555044
Download Count:
624
Copyright Info
© 1992, all rights reserved.
This open access ETD is published by Case Western Reserve University School of Graduate Studies and OhioLINK.