Title :
Local learning rules for spiking neurons with dendrite
Author :
Manette, Olivier F L
Author_Institution :
Centre Nat. de Rech. Scientifiques, UNIC, Gif-sur-Yvette, France
fDate :
July 31 2011-Aug. 5 2011
Abstract :
We present in this article four local rules to train a network of spiking dendritic neurons. After training, every neuron of the network becomes specialized for a particular feature of the input signal. With these rules, the network acts as a features extractor where each neuron contains a TAND vector, similar to logical AND but including information about time between the two events in the input signal.
Keywords :
learning (artificial intelligence); neural nets; TAND vector; features extractor; local learning rules; logical AND; network training; spiking dendritic neurons; spiking neurons; Biological system modeling; Feature extraction; Firing; Mathematical model; Neurons; Radio frequency;
Conference_Titel :
Neural Networks (IJCNN), The 2011 International Joint Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
978-1-4244-9635-8
DOI :
10.1109/IJCNN.2011.6033504
