Abstract
Learning methods for spiking neural networks are not as well developed as the traditional rate based networks, which widely use the back-propagation learning algorithm. We propose and implement an efficient Hebbian learning method with homeostasis for a network of spiking neurons. Similar to STDP, timing between spikes is used for synaptic modification. Homeostasis ensures that the synaptic weights are bounded and the learning is stable. The winner take all mechanism is also implemented to promote competitive learning among output neurons. We have implemented this method in a C++ object oriented code (called CSpike). We have tested the code on four images of Gabor filters and found bell-shaped tuning curves using 36 test set images of Gabor filters in different orientations. These bell-shapes curves are similar to those experimentally observed in the VI and MT/V5 area of the mammalian brain.
Original language | English (US) |
---|---|
Title of host publication | 2009 International Joint Conference on Neural Networks, IJCNN 2009 |
Pages | 1054-1060 |
Number of pages | 7 |
DOIs | |
State | Published - Nov 18 2009 |
Event | 2009 International Joint Conference on Neural Networks, IJCNN 2009 - Atlanta, GA, United States Duration: Jun 14 2009 → Jun 19 2009 |
Publication series
Name | Proceedings of the International Joint Conference on Neural Networks |
---|
Other
Other | 2009 International Joint Conference on Neural Networks, IJCNN 2009 |
---|---|
Country | United States |
City | Atlanta, GA |
Period | 6/14/09 → 6/19/09 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Software
- Artificial Intelligence
Cite this
}
Hebbian learning with winner take all for spiking neural networks. / Gupta, Ankur; Long, Lyle Norman.
2009 International Joint Conference on Neural Networks, IJCNN 2009. 2009. p. 1054-1060 5178751 (Proceedings of the International Joint Conference on Neural Networks).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Hebbian learning with winner take all for spiking neural networks
AU - Gupta, Ankur
AU - Long, Lyle Norman
PY - 2009/11/18
Y1 - 2009/11/18
N2 - Learning methods for spiking neural networks are not as well developed as the traditional rate based networks, which widely use the back-propagation learning algorithm. We propose and implement an efficient Hebbian learning method with homeostasis for a network of spiking neurons. Similar to STDP, timing between spikes is used for synaptic modification. Homeostasis ensures that the synaptic weights are bounded and the learning is stable. The winner take all mechanism is also implemented to promote competitive learning among output neurons. We have implemented this method in a C++ object oriented code (called CSpike). We have tested the code on four images of Gabor filters and found bell-shaped tuning curves using 36 test set images of Gabor filters in different orientations. These bell-shapes curves are similar to those experimentally observed in the VI and MT/V5 area of the mammalian brain.
AB - Learning methods for spiking neural networks are not as well developed as the traditional rate based networks, which widely use the back-propagation learning algorithm. We propose and implement an efficient Hebbian learning method with homeostasis for a network of spiking neurons. Similar to STDP, timing between spikes is used for synaptic modification. Homeostasis ensures that the synaptic weights are bounded and the learning is stable. The winner take all mechanism is also implemented to promote competitive learning among output neurons. We have implemented this method in a C++ object oriented code (called CSpike). We have tested the code on four images of Gabor filters and found bell-shaped tuning curves using 36 test set images of Gabor filters in different orientations. These bell-shapes curves are similar to those experimentally observed in the VI and MT/V5 area of the mammalian brain.
UR - http://www.scopus.com/inward/record.url?scp=70449421908&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70449421908&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2009.5178751
DO - 10.1109/IJCNN.2009.5178751
M3 - Conference contribution
AN - SCOPUS:70449421908
SN - 9781424435531
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 1054
EP - 1060
BT - 2009 International Joint Conference on Neural Networks, IJCNN 2009
ER -