KNOWLEDGE-BASED ENVIRONMENT FOR DEVELOPING AND TESTING EMBEDDED NEURAL NETWORKS

Award Information
Agency:
Department of Defense
Branch
Army
Amount:
$250,000.00
Award Year:
1994
Program:
SBIR
Phase:
Phase II
Contract:
n/a
Agency Tracking Number:
15755
Solicitation Year:
n/a
Solicitation Topic Code:
n/a
Solicitation Number:
n/a
Small Business Information
Tau Corp.
485 Alberto Wy, Los Gatos, CA, 95032
Hubzone Owned:
N
Socially and Economically Disadvantaged:
N
Woman Owned:
N
Duns:
n/a
Principal Investigator:
Peter Rothman
Principal Investigator
(408) 395-9191
Business Contact:
() -
Research Institution:
n/a
Abstract
NUMEROUS GOVERNMENT AND INDUSTRY RESEARCH AND DEVELOPMENT PROJECTS ARE EXPLORING THE APPLICATION OF NEURAL NETWORKS WITHIN EMBEDDED SOFTWARE SYSTEMS. ALTHOUGH MODELS, IMPLEMENTATIONS, AND APPLICATIONS OF NEURAL NET TECHNOLOGY ARE MULTIPLYING, LITTLE ATTENTION HAS BEEN PAID TO TESTING, BENCHMARKING, AND COMPARING THESE COMPUTATIONAL SYSTEMS. IN FACT, FOR MANY SPECIFIC NEURAL NETWORK ARCHITECTURES LITTLE IS KNOWN ABOUT THEIR CLASSIFICATION AND INFORMATION STORAGE CAPABILITIES. THERE DOES NOT EXIST A SIMPLE, WIDELY ACCEPTED, SET OF TEST CASES WHICH CAN BE UTILIZED TO COMPARE CANDIDATE NEURAL NETWORK ARCHITECTURE, AND EVALUATE THEIR APPLICABILITY TO SPECIFIC EMBEDDED APPLICATIONS. THE PURPOSE OF THIS PROJECT IS THE DEVELOPMENT OF A NEURAL NETWORK KNOWLEDGE-BASED (N2KB). THE N2KB WILL BE DESIGNED TO PROVIDE INFORMATION ON NEURAL NETWORK MODELS, RECOMMENDATIONS ON THE APPROPRIATE NEURAL NETWORK PARADIGMS TO USE IN SPECIFIC APPLICATIONS, FUNCTIONAL PROTOTYPES OF NEURAL NETWORKS, AND NETWORK DEBUGGING AND TESTING FACILITIES.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government