Original Contribution: Implementation of front-end processor neural networks

The following are citations selected by title and abstract as being related to AI, resulting from a computer search, using BRS Information Technologies, of the Dissertation Abstracts Online database produced by University Microfilms International (UMI).The online file includes abstracts, which are not published in this listing, but the citations below do include reference to the published Dissertation Abstracts International (DAI), which contains the abstracts. Other elements of the citation are author; university, degree, and, if available, number of pages; title; UMI order number and year-month of DAI; and one or more DAI subject descriptors chosen by the author of the dissertation. The listing may include masters abstracts, denoted by MAI (Masters Abstracts International) instead of DAI. References are sorted by subject descriptor; in the event that there is more than one descriptor, the first is used. Within each descriptor, entries are sorted by author.Unless otherwise specified, paper or microform copies of dissertations may be ordered from University Microfilms International, Dissertation Copies, Post Office Box 1764, Ann Arbor, MI 48106; telephone for U.S. (except Michigan, Hawaii, Alaska): 1-800-521-3042, for Canada: 1-800-268-6090. Price lists and other ordering and shipping information are in the introduction to the published DAI. Agriculture, Forestry and Wildlife

Selected M-Related Dissertations Bibliography

A framework for extremely compact, all analog, and massively parallel implementation of shunting recurrent and nonrecurrent neural networks that is applicable to a wide variety of FET-based integration technologies is proposed. A specific circuit designed for implementation with gallium arsenide MESFETs is implemented.
The implemented network's ability to perform contrast enhancement, data compression, and adaptation to mean input strength level, as well as its tunability of sensitivity, are well-suited for processing of sensory information in general and visual information in particular. Thus, if integrated with an array of photo-detectors, it can find widespread optoelectronics applications. These properties are also desirable for feature extraction for content addressable memory (CAM) systems. Furthermore, the network fits in self-organizing multilayer network architectures of Adaptive Resonance Theory.
The asymptotic global stability of the network is shown by finding a global Liapunov energy function, which serves to show that the network itself is capable of CAM. The time trace of the local activity of the implemented network is found via a variational analysis which leads to the identification of higher order kernels in a Volterra series expansion. The same mathematical techniques are applied to find higher order spatial kernels which explains the extraordinary high order classification properties embedded in simple multiplicative nonlinearity.

Bahram Nabet

Papers

Design, analysis, and gallium arsenide based implementation of a class of neural networks with application to vision and optoelectronics