Comparison of learning methods for spiking neural networks
- 96 Downloads
Investigation of different factor influence on the spike-timing-dependent plasticity learning process was performed. The next factors were analyzed: choice of spike pairing scheme, shapes of postsynaptic currents and the choice of input type signal for learning. Best factors for learning performance were extracted.
Keywordsspiking neural network learning methods neurosimulators STDP spike-pairing scheme
Unable to display preview. Download preview PDF.
- 2.Bichler, O., Querlioz, D., Thorpe, S.J., Bourgoin, J.-P., and Gamrat, C., Extraction of temporally correlated features from dynamic vision sensors with spike-timing-dependent plasticity, Neural Networks, 2012, no. 32, pp. 339–348.Google Scholar
- 3.Pichevar, R. and Rouat, J., Monophonic sound source separation with an unsupervised network of spiking neurons, Neurocomputing, 2007, no. 71, pp.109–120.Google Scholar
- 4.Chandhok, C. and Chaturvedi, S., Adaptation of spiking neural networks for image clustering, Int. J. Video Image Process. Network Security IJVIPNS-IJENS, 2003, no. 12.Google Scholar
- 5.Maass, W. and Markram, H., Synapses as dynamic memory buffers, Neural Networks, 2002, no. 15, pp. 155–161.Google Scholar
- 8.CSIM: A neural circuit SIMulator, The IGI LSM Group, Technical University, Graz 2002; URL: http://www.lsm.tugraz.at.