Obstacle to training SpikeProp networks - Cause of surges in training process

Proceedings of the International Joint Conference on Neural Networks

Volumn , Issue , 2009, Pages 3062-3066

  Takase, Haruhiko ^a   Fujita, Masaru ^a   Kawanaka, Hiroharu ^a   Tsuruoka, Shinji ^a   Kita, Hidehiko ^a   Hayashi, Terumine ^a  

^a MIE UNIVERSITY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

SPIKE-PROP ALGORITHM; SPIKING NEURAL NETWORKS; TRAINING PROCESS;

NEURAL NETWORKS;

LEARNING ALGORITHMS;

EID: 70449455867     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/IJCNN.2009.5178756     Document Type: Conference Paper

References (4)

1. S. M. Bohte, H. L. Poutre, and J. N. Kok, "Error-Backpropagation in Temporally Encoded Networks of Spiking Neurons, " Neurocomputing, vol. 48, pp. 17-37 (2002).
2. W. Maass, "Lower bounds for the computational power of networks of spiking neurons, " Neural Computation, vol. 8, pp. 1-40 (1996).
3. S. McKennoch, D. Liu, and L. G. Bushnell, "Fast Modifications of the SpikeProp Algorithm, " Proc. of 2006 International Joint Conference on Neural Networks, pp. 7701-7708 (2006).
4. Fujita M., Takase H., Kita H., Hayashi T., "Shape of error surfaces in SpikeProp, " Proc. of 2008 International Joint Conference on Neural Networks, pp. 841-845 (2008).