Memory versus non-linearity in reservoirs
- Author
- David Verstraeten (UGent) , Joni Dambre (UGent) , Xavier Dutoit and Benjamin Schrauwen (UGent)
- Organization
- Abstract
- Reservoir Computing (RC) is increasingly being used as a conceptually simple yet powerful method for using the temporal processing of recurrent neural networks (RNN). However, because fundamental insight in the exact functionality of the reservoir is as yet still lacking, in practice there is still a lot of manual parameter tweaking or brute-force searching involved in optimizing these systems. In this contribution we aim to enhance the insights into reservoir operation, by experimentally studying the interplay of the two crucial reservoir properties, memory and non-linear mapping. For this, we introduce a novel metric which measures the deviation of the reservoir from a linear regime and use it to define different regions of dynamical behaviour. Next, we study the relationship of two important reservoir parameters, input scaling and spectral radius, on two properties of an artificial task, namely memory and non- linearity.
- Keywords
- Reservoir Computing, machine learning, neural networks
Downloads
-
(...).pdf
- full text
- |
- UGent only
- |
- |
- 299.58 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-1024070
- MLA
- Verstraeten, David, et al. “Memory versus Non-Linearity in Reservoirs.” IEEE International Joint Conference on Neural Networks (IJCNN), IEEE, 2010, doi:10.1109/IJCNN.2010.5596492.
- APA
- Verstraeten, D., Dambre, J., Dutoit, X., & Schrauwen, B. (2010). Memory versus non-linearity in reservoirs. IEEE International Joint Conference on Neural Networks (IJCNN). Presented at the 2010 IEEE International joint conference on Neural Networks (IJCNN 2010) ; World congress on Computational Intelligence (WCCI 2010), Barcelona, Spain. https://doi.org/10.1109/IJCNN.2010.5596492
- Chicago author-date
- Verstraeten, David, Joni Dambre, Xavier Dutoit, and Benjamin Schrauwen. 2010. “Memory versus Non-Linearity in Reservoirs.” In IEEE International Joint Conference on Neural Networks (IJCNN). New York, NY, USA: IEEE. https://doi.org/10.1109/IJCNN.2010.5596492.
- Chicago author-date (all authors)
- Verstraeten, David, Joni Dambre, Xavier Dutoit, and Benjamin Schrauwen. 2010. “Memory versus Non-Linearity in Reservoirs.” In IEEE International Joint Conference on Neural Networks (IJCNN). New York, NY, USA: IEEE. doi:10.1109/IJCNN.2010.5596492.
- Vancouver
- 1.Verstraeten D, Dambre J, Dutoit X, Schrauwen B. Memory versus non-linearity in reservoirs. In: IEEE International Joint Conference on Neural Networks (IJCNN). New York, NY, USA: IEEE; 2010.
- IEEE
- [1]D. Verstraeten, J. Dambre, X. Dutoit, and B. Schrauwen, “Memory versus non-linearity in reservoirs,” in IEEE International Joint Conference on Neural Networks (IJCNN), Barcelona, Spain, 2010.
@inproceedings{1024070, abstract = {{Reservoir Computing (RC) is increasingly being used as a conceptually simple yet powerful method for using the temporal processing of recurrent neural networks (RNN). However, because fundamental insight in the exact functionality of the reservoir is as yet still lacking, in practice there is still a lot of manual parameter tweaking or brute-force searching involved in optimizing these systems. In this contribution we aim to enhance the insights into reservoir operation, by experimentally studying the interplay of the two crucial reservoir properties, memory and non-linear mapping. For this, we introduce a novel metric which measures the deviation of the reservoir from a linear regime and use it to define different regions of dynamical behaviour. Next, we study the relationship of two important reservoir parameters, input scaling and spectral radius, on two properties of an artificial task, namely memory and non- linearity.}}, author = {{Verstraeten, David and Dambre, Joni and Dutoit, Xavier and Schrauwen, Benjamin}}, booktitle = {{IEEE International Joint Conference on Neural Networks (IJCNN)}}, isbn = {{9781424469178}}, issn = {{1098-7576}}, keywords = {{Reservoir Computing,machine learning,neural networks}}, language = {{eng}}, location = {{Barcelona, Spain}}, pages = {{8}}, publisher = {{IEEE}}, title = {{Memory versus non-linearity in reservoirs}}, url = {{http://doi.org/10.1109/IJCNN.2010.5596492}}, year = {{2010}}, }
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: