Title :
Implementing position-invariant detection of feature-conjunctions in a network of spiking neurons
Author :
Bohte, Sander M. ; Kok, Joost N. ; La Poutré, Han
Author_Institution :
CWI, Amsterdam, Netherlands
fDate :
6/24/1905 12:00:00 AM
Abstract :
The design of neural networks that are able to efficiently detect conjunctions of features is an important open challenge. We develop a feedforward spiking neural network that requires a constant number of neurons for detecting a conjunction irrespective of the size of the retinal input field, and for up to four simultaneously present feature-conjunctions
Keywords :
data structures; feature extraction; feedforward neural nets; learning (artificial intelligence); context dependent thinning; data-structure; feature conjunction; feature extraction; feedforward neural networks; neural network architecture; position-invariant detection; relative proximity; spiking neurons; unsupervised learning; Computer vision; Detectors; Encoding; Feedforward neural networks; Feedforward systems; Intelligent networks; Neural networks; Neurons; Retina; Technology management;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007647
