Boosted backpropagation learning for training deep modular networks

ICML 2010 - Proceedings, 27th International Conference on Machine Learning

Volumn , Issue , 2010, Pages 407-414

  Grubb, Alexander ^a   Bagnell, J Andrew ^a  

^a Carnegie Mellon University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BACKPROPAGATION LEARNING; DIVIDE AND CONQUER; ERROR PROPAGATION; EXISTING SYSTEMS; FUNCTIONAL MODULES; GRADIENT DESCENT; HARD PROBLEMS; LEARNING MACHINES; LOCAL OPTIMA; MODULAR LEARNING; MODULAR NETWORK; PARAMETER SPACES; SEPARATION OF CONCERNS; SIMPLE ALGORITHM;

BACKPROPAGATION; HETEROGENEOUS NETWORKS; LEARNING SYSTEMS; MECHANICS;

LEARNING ALGORITHMS;

EID: 77956534703     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (20)

1. Bengio, Y., Lamblin, P., Popovici, D. and Larochelle, H. Greedy layer-wise training of deep networks. In Advances in Neural Information Processing Systems 19. MIT Press. 2007.
2. Bottou, L. and Gallinari, P. A framework for the cooperation of learning algorithms. In Advances in Neural Information Processing Systems, pp. 781-788, 1991.
3. Bradley, D. M. Learning in Modular Systems. PhD thesis, The Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA, 2009.
4. Freund, Y. and Schapire, R. E. Experiments with a new boosting algorithm. In Proc. of the 13th International Conference on Machine Learning (ICML 1996), pp. 148- 156, 1996.
5. Friedman, J. H. Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29:1189- 1232, 2000.
6. Gelfand, I. M. and Fomin, S. V. Calculus of Variations. Dover Publications, October 2000.
7. Grubb, A. and Bagnell, J. A. Boosted backpropagation learning for deep modular networks. Technical report, CMU-RI-09-45, 2010.
8. Hinton, G. E., Osindero, S. and Teh, Y. A fast learning algorithm for deep belief nets. Neural Computation, 18 :1527-1554, 2006.
9. Kivinen, J., Smola, A. J. and Williamson, R. C. Online learning with kernels. IEEE Trans, on Signal Proc., 52(8):2165-2176, 2004.
10. Larochelle, H., Bengio, Y., Louradour, J. and Lamblin, P. Exploring strategies for training deep neural networks. Journal of Machine Learning Research, 10:1-40, 2009.
11. Lawrence, S., Giles, C. L. and Fong, S. Natural language grammatical inference with recurrent neural networks. IEEE Trans, on Knowl. and Data Eng., 12(1):126-140, 2000.
12. LeCun, Y. A theoretical framework for back-propagation. In Proc. of the 1988 Connectionist Models Summer School, pp. 21-28, 1988.
13. LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P. Gradient-based learning applied to document recognition. Proc. of the IEEE, 86(11) : 2278-2324, 1998.
14. Mason, L., Baxter, J., Bartlett, P. L. and Frean, M. Functional gradient techniques for combining hypotheses. In Advances in Large Margin Classifiers. MIT Press, 1999.
15. Ratliff, N., Silver, D. and Bagnell, J. A. Learning to search: Functional gradient techniques for imitation learning. Autonomous Robots, 27(1):25-53, July 2009.
16. Rohde, D. L. T. A connectionist model of sentence comprehension and production. PhD thesis, Carnegie Mellon University, PA, USA, 2002.
17. Rumelhart, D. E., Hinton, G. E. and Williams, R. J. Learning internal representations by error propagation. Computational Models Of Cognition And Perception Series, pp. 318-362, 1986.
18. Scholkopf, B. and Smola, A. J. Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge, MA, USA, 2001.
19. Werbos, Paul John. The roots of backpropagation: from ordered derivatives to neural networks and political forecasting. Wiley-Interscience, New York, NY, USA, 1994.
20. Zucker, M., Bagnell, J. A., Atkeson, C. and Kuffner, J. An optimization and learning approach to rough terrain locomotion. In International Conference on Robotics and Automation, To Appear, 2010.