NTRS - NASA Technical Reports Server

Back to Results
Connectivity strategies for higher-order neural networks applied to pattern recognitionDifferent strategies for non-fully connected HONNs (higher-order neural networks) are discussed, showing that by using such strategies an input field of 128 x 128 pixels can be attained while still achieving in-plane rotation and translation-invariant recognition. These techniques allow HONNs to be used with the larger input scenes required for practical pattern-recognition applications. The number of interconnections that must be stored has been reduced by a factor of approximately 200,000 in a T/C case and about 2000 in a Space Shuttle/F-18 case by using regional connectivity. Third-order networks have been simulated using several connection strategies. The method found to work best is regional connectivity. The main advantages of this strategy are the following: (1) it considers features of various scales within the image and thus gets a better sample of what the image looks like; (2) it is invariant to shape-preserving geometric transformations, such as translation and rotation; (3) the connections are predetermined so that no extra computations are necessary during run time; and (4) it does not require any extra storage for recording which connections were formed.
Document ID
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Spirkovska, Lilly
(NASA Ames Research Center Moffett Field, CA, United States)
Reid, Max B.
(NASA Ames Research Center Moffett Field, CA, United States)
Date Acquired
August 15, 2013
Publication Date
January 1, 1990
Subject Category
Meeting Information
Meeting: IJCNN - International Joint Conference on Neural Networks
Location: San Diego, CA
Country: United States
Start Date: June 17, 1990
End Date: June 21, 1990
Sponsors: IEEE, International Nueral Network Society
Accession Number
Distribution Limits

Available Downloads

There are no available downloads for this record.
No Preview Available