Abstract
An extended Hamming neural network structure is proposed for recognition of non binary input patterns. Proposed structure is based on splitting the input pattern into N binary input patterns, where N is the number of bits used for representing each pixel of the original input pattern. Subsequently each binary pattern is processed for a Hamming neural network. Finally the outputs of each binary neural network are used to identify the non binary input pattern. Simulation results show that proposed structures performs fairly well for input patterns with 40% of their pixels distorted.
Original language | English |
---|---|
Pages | 607-609 |
Number of pages | 3 |
State | Published - 1994 |
Externally published | Yes |
Event | Proceedings of the 37th Midwest Symposium on Circuits and Systems. Part 2 (of 2) - Lafayette, LA, USA Duration: 3 Aug 1994 → 5 Aug 1994 |
Conference
Conference | Proceedings of the 37th Midwest Symposium on Circuits and Systems. Part 2 (of 2) |
---|---|
City | Lafayette, LA, USA |
Period | 3/08/94 → 5/08/94 |