Reservoir regularization stabilizes learning of Echo State Networks with output feedback

ESANN 2011 proceedings, 19th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Volumn , Issue , 2010, Pages 59-64

  Reinhart, René Felix ^a   Steil, Jochen Jakob ^a  

^a BIELEFELD UNIVERSITY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ECHO STATE NETWORKS; ERROR AMPLIFICATION; OUTPUT FEEDBACK; PARAMETER DEPENDENCY; PARAMETERIZED; PATTERN GENERATION; REDUCTION OF ERRORS; RESERVOIR NETWORKS;

ARTIFICIAL INTELLIGENCE; COGNITIVE SYSTEMS; COMPUTATIONAL METHODS; SOFTWARE ENGINEERING;

NEURAL NETWORKS;

EID: 84887039818     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. H. Jaeger, M. Lukosevicius, D. Popovici, and U. Siewert. Optimization and applications of echo state networks with leaky-integrator neurons. Neural Networks, 20 (3): 335-352, 2007.
2. F. wyffels, B. Schrauwen, and D. Stroobandt. Stable output feedback in reservoir computing using ridge regression. In ICANN, pages 808-817, 2008.
3. F. wyffels and B. Schrauwen. Design of a central pattern generator using reservoir computing for learning human motion. In ECSIS Symp. on LAB-RS, pages 118-122, 2009.
4. A. F. Krause, B. Bläsing, V. Dürr, and T. Schack. Direct control of an active tactile sensor using echo state networks. In Human Centered Robot Systems, volume 6, pages 11-21. Springer, 2009.
5. R. F. Reinhart and J. J. Steil. Recurrent neural associative learning of forward and inverse kinematics for movement generation of the redundant PA-10 robot. In ECSIS Symp. on LAB-RS, pages 35-40, 2008.
6. E. Antonelo, B. Schrauwen, and J. V. Campenhout. Generative modeling of autonomous robots and their environments using reservoir computing. Neural Processing Letters, 26 (3): 233-249, 2007.
7. D. Sussillo and L. F. Abbott. Generating coherent patterns of activity from chaotic neural networks. Neuron, 63: 544-557, 2009.
8. R. F. Reinhart and J. J. Steil. A constrained regularization approach for input-driven recurrent neural networks. Differ. Equ. Dyn. Syst. DOI: 10.1007/s12591-010-0067-x.
9. Herbert Jaeger. Reservoir self-control for achieving invariance against slow input distortions. Technical Report 23, Jacobs University, Oct. 2010.