Approach for real – time image recognition
Автор
Kozhemyako, V. P.
Tymchenko, L. I.
Kutaev, Yu. F.
Yaroviy, A. A.
Кожем’яко, В. П.
Тимченко, Л. І.
Кутаєв, Ю. Ф.
Яровий, А. А.
Дата
2001Metadata
Показати повну інформаціюCollections
- Наукові роботи каф. КН [813]
Анотації
In this work new approach for parallel-hierarchical (PH) networks learning1 having applied to
the real-time image sequences in extended laser paths2 is proposed. It's possible to synthesize PH network
with learning abilities by using the general idea of artificial neural networks structured organizations on the
scheme: input layer - hidden layer – output layer. The 1-st network level should be used as input layer, next
levels should be used as a hidden layer and the last level should be used as an output one, as it is
traditionally in artificial neural networks.
URI:
http://ir.lib.vntu.edu.ua//handle/123456789/18011