VERSATILE NEURAL RING ARCHITECTURES FOR VISION AND NATURAL LANGUAGE PROCESSING APPLICATIONS

Award Information
Agency:
Department of Defense
Branch:
Air Force
Amount:
$60,000.00
Award Year:
1990
Program:
SBIR
Phase:
Phase II
Contract:
N/A
Agency Tracking Number:
9521
Solicitation Year:
N/A
Solicitation Topic Code:
N/A
Solicitation Number:
N/A
Small Business Information
Caelum Research Corp.
11229 Lockwood Dr, Silver Spring, MD, 20901
Hubzone Owned:
N
Socially and Economically Disadvantaged:
N
Woman Owned:
N
Duns:
N/A
Principal Investigator
 Dr Panos A Ligomenides
 (301) 593-1748
Business Contact
Phone: () -
Research Institution
N/A
Abstract
VISION AND NATURAL LANGUAGE PROCESSING IS BASED ON INDUCTIVE INFERENCE, WHICH IS REALIZABLE BY LARGE SCALE NEURAL NETWORKS. CONSTRUCTING FULLY PARALLEL, LARGE SCALE, NEURAL NETWORKS IS FRUSTRATED BY THE PROBLEMS OF PROVIDING FOR MASSIVE INTER-CONNECTIVITYAND FOR OVERCOMING FAN IN/OUT LIMITATIONS IN AREA-EFFICIENT VLSI/WSI REALIZATIONS. A MODULAR BUSED NEURAL RING (MBNR) ARCHITECTURE IS PROPOSED HEREIN, WHICH SOLVES THESE PROBLEMS. ITS REAL TIME DYNAMIC EXPANDABILITY AND RECONFIGURABILITY ALLOWS FOR ON-LINE EXPERIMENTATIONAND TESTING OF NEURAL MODELS AND MECHANISMS, CONCERNING APPLICATIONS TO VISION AND NATURAL LANGUAGE PROCESSING. IN THIS PROJECT WE PROPOSE A PHASE I INVESTIGATION OF FEASIBILITY OF THE MBNR ARCHITECTURE AND ITS SUITABILITY FOR IMPLEMENTATION AND PERFORMANCE EVALUATION OF NEURAL MODELS FOR VISION AND NATURAL LANGUAGE PROCESSING.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government