Type of Document Dissertation Author Schinazi, Robert Glen Author's Email Address reasor@VTVM1.cc.vt.edu URN etd-42598-01830 Title Designing Massive 3-Dimensional Neural Networks with Chromosomal-Based Simulated Development Degree PhD Department Industrial and Systems Engineering Advisory Committee
Advisor Name Title Reasor, Roderick J. Committee Chair Lu, Guo-Quan Committee Member Rees, Loren Paul Committee Member Sarin, Subhash C. Committee Member Sullivan, William G. Committee Member Keywords
- Neural Network
- Cerebral cortex
- automata simulation
- cell growth simulation
- cell growth modeling
Date of Defense 1995-12-04 Availability unrestricted AbstractDesigning Massive 3-Dimensional Neural Networks with
Chromosomal-Based Simulated Development
By Robert Glen Schinazi
A technique for designing and optimizing the next generation of smart process controllers
has been developed in this dissertation. The literature review indicated that neural networks held
the most promise for this application, yet fundamental limitations have prevented their
introduction to commercial settings thus far. This fundamental limitation has been overcome
through the enhancement of neural network theory.
The approach taken in this research was to produce highly intelligent process control
systems by accurately modeling the nervous structures of higher biological organisms. The
mammalian cerebral cortex was selected as the primary model since it is the only computational
element capable of interpreting and complex patterns that develop over time. However the choice
of the mammalian cerebral cortex as the model introduced two new levels of network complexity.
First, the cerebral cortex is a three dimensional structure with extremely complicated patterns of
interconnectivity. Second, the structure of the cerebral cortex can only be realized when
thousands or millions of neurons are integrated into a massive scale neural network. The neural
networks developed in this research were designed around the Hebbian adaptation, the only
training technique proven by the literature review to be applicable to massive scale networks.
These design difficulties were resolved by not only modeling the cerebral cortex, but the
process by which it develops and evolves in biological systems. To complete this model, an
advanced genetic algorithm was produced, and a technique was developed to encode all
functional and structural parameters that define the cerebral cortex into the artificial chromosome.
The neural networks were designed by a cell growth simulation program that decoded the
structural and functional information on the chromosome. The cell growth simulation program is
capable of producing patterns of differentiation unique for any slight variations in the genetic
parameters. These growth patterns are similar to patterns of cellular differentiation seen in
biological systems. While the computational resources needed to implement a massive scale
neural network are beyond that available in existing computer systems, the technique has
produced output lists which fully define the interconnections and functional characteristic of the
neurons, thereby laying the foundation for their future use in process control.
Filename Size Approximate Download Time (Hours:Minutes:Seconds)
28.8 Modem 56K Modem ISDN (64 Kb) ISDN (128 Kb) Higher-speed Access R_Schinazi_PhD_Final.pdf 4.19 Mb 00:19:23 00:09:58 00:08:43 00:04:21 00:00:22
If you have questions or technical problems, please Contact DLA.