TY - GEN
T1 - Spiking neural networks to detect temporal patterns
AU - Zuters, Janis
PY - 2009
Y1 - 2009
N2 - Spiking neural networks (SNNs) are more powerful than their non-spiking predecessors as they can encode temporal information in their signals, but they also need different and biologically more plausible rules for synaptic plasticity. In this paper, an unsupervised learning algorithm is introduced for a spiking neural network. The algorithm is based on the Hebbian rule, with the addition of the principle of adapting a layer activation level so as to guarantee frequent firings of neurons for each layer. The proposed algorithm has been illustrated with experimental results related to the detection of temporal patterns in an input stream.
AB - Spiking neural networks (SNNs) are more powerful than their non-spiking predecessors as they can encode temporal information in their signals, but they also need different and biologically more plausible rules for synaptic plasticity. In this paper, an unsupervised learning algorithm is introduced for a spiking neural network. The algorithm is based on the Hebbian rule, with the addition of the principle of adapting a layer activation level so as to guarantee frequent firings of neurons for each layer. The proposed algorithm has been illustrated with experimental results related to the detection of temporal patterns in an input stream.
KW - Adaptive activation
KW - Spiking neural networks
KW - Temporal patterns
KW - Unsupervised learning
UR - https://www.scopus.com/pages/publications/72749084624
U2 - 10.3233/978-1-58603-939-4-131
DO - 10.3233/978-1-58603-939-4-131
M3 - Conference paper
AN - SCOPUS:72749084624
SN - 9781586039394
T3 - Frontiers in Artificial Intelligence and Applications
SP - 131
EP - 142
BT - Databases and Information Systems V
PB - IOS Press
ER -