A Hierarchical Net-Structure Learning System for Pattern Description
File(s)
Date
1974Author
Williams, Harold Addison Jr.
Publisher
University of Wisconsin-Madison Department of Computer Sciences
Metadata
Show full item recordAbstract
This thesis discusses a computer program that recognizes and describes two-dimensional patterns and the subpatterns composing those patterns, outputting names, locations and sizes of both patterns and subpatterns. The program also recognizes all patterns in a scene consisting of several patterns .
Patterns are stored in a hierarchical, net-structure permanent memory, which is completely learned as a result of simple feedback from a trainer. Weighted links between memory nodes represent subpattern/pattern relationships. The memory is homogeneous, for subpatterns are represented in terms of primitive features in the same manner that patterns are represented in terms of subpatterns. A short term memory is used to store instances of permanent memory information during
recognition.
Pattern recognition is accomplished with a serial heuristic-search algorithm, unusual for a pattern recognition program, which attempts to search memory and compute input properties efficiently. Without special processing, the program can be asked to look for all occurrences af a specified pattern in an input scene.
Permanent Link
http://digital.library.wisc.edu/1793/57842Citation
TR199