Improving reservoirs using intrinsic plasticity

Neurocomputing

Volumn 71, Issue 7-9, 2008, Pages 1159-1171

  Schrauwen, Benjamin ^a   Wardermann, Marion ^a   Verstraeten, David ^a   Steil, Jochen J ^b   Stroobandt, Dirk ^a  

^a GHENT UNIVERSITY   (Belgium)

^b BIELEFELD UNIVERSITY   (Germany)

Author keywords

Information maximization; Intrinsic plasticity; Reservoir computing

Indexed keywords

LEARNING ALGORITHMS; NEURAL NETWORKS; OPTIMIZATION; PROBABILITY DENSITY FUNCTION;

INFORMATION MAXIMIZATION; INTRINSIC PLASTICITY; RESERVOIR COMPUTING;

DATA PROCESSING;

ARTICLE; ARTIFICIAL NEURAL NETWORK; CONTROLLED STUDY; INFORMATION PROCESSING; KERNEL METHOD; LEARNING ALGORITHM; LINEAR SYSTEM; MACHINE LEARNING; MATHEMATICAL COMPUTING; NERVE CELL PLASTICITY; NORMAL DISTRIBUTION; ONLINE ANALYTICAL PROCESSING; PRIORITY JOURNAL; PROCESS CONTROL; TASK PERFORMANCE; THEORETICAL STUDY; WORKING MEMORY;

EID: 40649085253     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2007.12.020     Document Type: Article

References (49)

1. Atick J.J. Could information theory provide an ecological theory of sensory processing?. Network: Comput. Neural Syst. 3 2 (1992) 213-251
2. Atiya A.F., and Parlos A.G. New results on recurrent network training: unifying the algorithms and accelerating convergence. IEEE Trans. Neural Networks 11 (2000) 697
3. Baddeley R., Abbott L.F., Booth M.C.A., Sengpiel F., Freeman T., Wakeman E.A., and Rolls E.T. Responses of neurons in primary and inferior temporal visual cortices to natural scenes. Proceedings in Biological Sciences vol. 264 (1997) 1775-1783
4. H. Burgsteiner, Training networks of biological realistic spiking neurons for real-time robot control, in: Proceedings of the 9th International Conference on Engineering Applications of Neural Networks, Lille, France, 2005, pp. 129-136.
5. H. Burgsteiner, On learning with recurrent spiking neural networks and their applications to robot control with real-world devices, Ph.D. Thesis, Graz University of Technology, 2005.
6. Bush K., and Anderson C. Modeling reward functions for incomplete state representations via echo state networks. Proceedings of the International Joint Conference on Neural Networks (2005), Montreal, Quebec
7. Destexhe A., and Marder E. Plasticity in single neuron and circuit computations. Nature 431 (2004) 789-795
8. Field D.J. What is the goal of sensory coding?. Neural Comput. 6 (1994) 559-601
9. B. Hammer, J.J. Steil, Perspectives on learning with recurrent neural networks, in: Proceedings of the European Symposium on Artificial Neural Networks (ESANN), 2002.
10. Hertzberg J., Jaeger H., and Schönherr F. Learning to ground fact symbols in behavior-based robots. Proceedings of the 15th European Conference on Artificial Intelligence (2002) 708-712
11. H. Jaeger, The "echo state" approach to analysing and training recurrent neural networks, Technical Report GMD Report 148, German National Research Center for Information Technology, 2001.
12. H. Jaeger, Short term memory in echo state networks, Technical Report GMD Report 152, German National Research Center for Information Technology, 2001.
13. H. Jaeger, Adaptive nonlinear system identification with echo state networks, in: Advances in Neural Information Processing Systems, 2003, pp. 593-600.
14. Jaeger H. Reservoir riddles: suggestions for echo state network research (extended abstract). Proceedings of the International Joint Conference on Neural Networks (2005) 1460-1462
15. Jaeger H., and Haas H. Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless telecommunication. Science 308 (2004) 78-80
16. P. Joshi, W. Maass, Movement generation and control with generic neural microcircuits, in: Proceedings of BIO-AUDIT, 2004, pp. 16-31.
17. Lazar A., Pipa G., and Triesch J. Fading memory and times series prediction in recurrent networks with different forms of plasticity. Neural Networks 20 3 (2007) 312-322
18. Maass W., Legenstein R.A., and Markram H. A new approach towards vision suggested by biologically realistic neural microcircuit models. Proceedings of the 2nd Workshop on Biologically Motivated Computer Vision, Lecture Notes in Computer Science (2002), Springer, Berlin
19. W. Maass, T. Natschläger, M.H., Fading memory and kernel properties of generic cortical microcircuit models, J. Physiol. 98(4-6) (2004) 315-330.
20. Maass W., Natschläger T., and Markram H. Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput. 14 11 (2002) 2531-2560
21. Maass W., Natschläger T., and Markram H. A model for real-time computation in generic neural microcircuits. Proceedings of NIPS vol. 15 (2003), MIT Press 229-236
22. Oubbati M., Levi P., Schanz M., and Buchheim T. Velocity control of an omnidirectional robocup player with recurrent neural networks. Proceedings of the Robocup Symposium (2005) 691-701
23. Ozturk M.C., Xu D., and Principe J.C. Analysis and design of echo state networks. Neural Comput. 19 (2006) 111-138
24. Plöger P.G., Arghir A., Günther T., and Hosseiny R. Echo state networks for mobile robot modeling and control. RoboCup 2003: Robot Soccer World Cup VII (2004) 157-168
25. G.V. Puskorius, F.L.A., Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks, IEEE Trans. Neural Networks 5 (1994) 279-297.
26. Rao Y., Kim S.-P., Sanchez J., Erdogmus D., Principe J., Carmena J., Lebedev M., and Nicolelis M. Learning mappings in brain machine interfaces with echo state networks. Proceedings of the 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing (2005) 233-236
27. Rumelhart D., Hinton G., and Williams R. Learning internal representations by error propagation, Parallel Distributed Processing (1986), MIT Press, Cambridge, MA
28. Salmen M., and Plöger P.G. Echo state networks used for motor control. Proceedings of the 2005 IEEE International Conference on Robotics and Automation (2005) 1953-1958
29. Schiller U.D., and Steil J.J. Analyzing the weight dynamics of recurrent learning algorithms. Neurocomputing 63C (2005) 5-23
30. Schmidhuber J., and Hochreiter S. Long short-term memory. Neural Comput. 9 (1997) 1735-1780
31. B. Schrauwen, J. Defour, D. Verstraeten, J. Van Campenhout, The introduction of time-scales in reservoir computing, applied to isolated digits recognition, in: Proceedings of the International Conference on Artificial Neural Networks (ICANN), 2007.
32. M.D. Skowronski, J.G. Harris, Minimum mean squared error time series classification using an echo state network prediction model, in: IEEE International Symposium on Circuits and Systems, 2006.
33. Special issue on echo state networks and liquid State machines, Neural Networks 20 (3).
34. Steil J.J. Backpropagation-decorrelation: online recurrent learning with O(N) complexity. Proceedings of the International Joint Conference on Neural Networks (IJCNN) vol. 1 (2004) 843-848
35. J.J. Steil, Memory in backpropagation-decorrelation O(N) efficient online recurrent learning, in: Proceedings of the International Conference on Artificial Neural Networks (ICANN), 2005.
36. Steil J.J. Online stability of backpropagation-decorrelation recurrent learning. Neurocomputing 69 (2006) 642-650
37. Steil J.J. Several ways to solve the mso problem. Proceedings of the European Symposium on Artificial Neural Networks (ESANN) (2007) 489-494
38. Steil J.J. Online reservoir adaptation by intrinsic plasticity for backpropagation-decorrelation and echo state learning. Neural Networks 20 3 (2007) 353-364
39. Takens F. Detecting strange attractors in turbulence. In: Rand D.A., and Young L.S. (Eds). Dynamical Systems and Turbulence, Lecture Notes in Mathematics vol. 898 (1981), Springer, Berlin 366-381
40. Triesch J. A gradient rule for the plasticity of a neuron's intrinsic excitability. Proceedings of the International Conference on Artificial Neural Networks (ICANN) (2005)
41. Triesch J. Synergies between intrinsic and synaptic plasticity mechanisms. Neural Comput. 19 (2007) 885-909
42. Verstraeten D., Schrauwen B., D'Haene M., and Stroobandt D. A unifying comparison of reservoir computing methods. Neural Networks 20 (2007) 391-403
43. Verstraeten D., Schrauwen B., and Stroobandt D. Isolated word recognition using a liquid state machine. Proceedings of the 13th European Symposium on Artificial Neural Networks (ESANN) (2005) 435-440
44. Verstraeten D., Schrauwen B., and Stroobandt D. Reservoir-based techniques for speech recognition. Proceedings of the World Conference on Computational Intelligence (2006) 1050-1053
45. Verstraeten D., Schrauwen B., Stroobandt D., and Van Campenhout J. Isolated word recognition with the liquid state machine: a case study. Inf. Process. Lett. 95 6 (2005) 521-528
46. Wardermann M., and Steil J.J. Intrinsic plasticity for reservoir learning algorithms. Proceedings of the European Symposium on Artificial Neural Networks (ESANN) (2007) 513-518
47. P.J. Werbos, Beyond regression: new tools for prediction and analysis in the behavioral sciences, Ph.D. Thesis, Applied Mathematics, Harvard University, Boston, MA, 1974.
48. Werbos P.J. Backpropagation through time: what it does and how to do it. Proc. IEEE 78 10 (1990) 1550-1560
49. Zhang W., and Linden D.J. The other side of the engram: experience-driven changes in neuronal intrinsic excitability. Nat. Rev. Neurosci. 4 (2003) 885-900