Advanced search
Author
Organization
Abstract
Reservoir Computing is a novel method in the field of neural networks and machine learning, which combines the computational power of a nonlinear dynamic system with the ease of training of a linear classifier. The basic setup is as follows: a sufficiently complex network of nonlinear nodes (called the reservoir) is excited by an input signal, and the instantaneous dynamic response of the system is then used to train a simple linear readout function.
Keywords
Cellular Neural Networks, Reservoir Computing

Citation

Please use this url to cite or link to this publication:

Chicago
Verstraeten, David, Samuel Xavier-de-Souza, Benjamin Schrauwen, Johan Suykens, Dirk Stroobandt, and Joos Vandewalle. 2008. “Pattern Classification with CNNs as Reservoirs.” In Proceedings of the International Symposium on Nonlinear Theory and Its Applications (NOLTA).
APA
Verstraeten, D., Xavier-de-Souza, S., Schrauwen, B., Suykens, J., Stroobandt, D., & Vandewalle, J. (2008). Pattern classification with CNNs as reservoirs. Proceedings of the International Symposium on Nonlinear Theory and its Applications (NOLTA). Presented at the International Symposium on Nonlinear Theory and its Applications (NOLTA).
Vancouver
1.
Verstraeten D, Xavier-de-Souza S, Schrauwen B, Suykens J, Stroobandt D, Vandewalle J. Pattern classification with CNNs as reservoirs. Proceedings of the International Symposium on Nonlinear Theory and its Applications (NOLTA). 2008.
MLA
Verstraeten, David, Samuel Xavier-de-Souza, Benjamin Schrauwen, et al. “Pattern Classification with CNNs as Reservoirs.” Proceedings of the International Symposium on Nonlinear Theory and Its Applications (NOLTA). 2008. Print.
@inproceedings{678913,
  abstract     = {Reservoir Computing is a novel method in the field of neural networks and machine learning, which combines the computational power of a nonlinear dynamic system with the ease of training of a linear classifier. The basic setup is as follows: a sufficiently complex network of nonlinear nodes (called the reservoir) is excited by an input signal, and the instantaneous dynamic response of the system is then used to train a simple linear readout function.},
  author       = {Verstraeten, David and Xavier-de-Souza, Samuel and Schrauwen, Benjamin and Suykens, Johan and Stroobandt, Dirk and Vandewalle, Joos},
  booktitle    = {Proceedings of the International Symposium on Nonlinear Theory and its Applications (NOLTA)},
  keyword      = {Cellular Neural Networks,Reservoir Computing},
  language     = {eng},
  location     = {Budapest, Hungary},
  pages        = {4},
  title        = {Pattern classification with CNNs as reservoirs},
  year         = {2008},
}