Feature deactivation using partial inhibitory networks during multiple object recognition
Refereed conference paper presented and published in conference proceedings


Full Text

Times Cited

Other information
AbstractThe author discusses the activation and deactivation phenomenon in a backpropagation network. The failure of the excitatory network to distinguish certain input patterns is explained by using the IT example. In a character recognition problem, the characters I and T have a very special characteristic; the letter I is embodied in the letter T. The partial inhibitory network is introduced. It can perform feature deactivation and multiple object recognition, and is applicable to this type of problem. The deductive factor increases the performance in multiple object recognition but increases the training time.
All Author(s) ListChan Lai-Wan
Name of ConferenceInternational Joint Conference on Neural Networks - IJCNN-91-Seattle
Start Date of Conference08/07/1991
End Date of Conference12/07/1991
Place of ConferenceSeattle, WA, USA
Country/Region of ConferenceUnited States of America
Year1991
Month12
Day1
Pages199 - 204
ISBN0780301641
LanguagesEnglish-United Kingdom

Last updated on 2020-29-05 at 00:17