Abstract
Recently, there has been an increased interest in machine learning methods that transfer knowledge across multiple learning tasks and “learn to learn.” Such methods have repeatedly been found to outperform conventional, single-task learning algorithms when the learning tasks are appropriately related. To increase robustness of such approaches, methods are desirable that can reason about the relatedness of individual learning tasks, in order to avoid the danger arising from tasks that are unrelated and thus potentially misleading.
This paper describes the task-clustering (TC) algorithm. TC clusters learning tasks into classes of mutually related tasks. When facing a new learning task, TC first determines the most related task cluster, then exploits information selectively from this task cluster only. An empirical study carried out in a mobile robot domain shows that TC outperforms its non-selective counterpart in situations where only a small number of tasks is relevant.1
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Y. S. Abu-Mostafa. A method for learning from hints. In S. J. Hanson, J. Cowan, and C. L. Giles, editors, Advances in Neural Information Processing Systems 5, pages 73–80, San Mateo, CA, 1993. Morgan Kaufmann.
W.-K. Ahn and W. F. Brewer. Psychological studies of explanation-based learning. In G. DeJong, editor, Investigating Explanation-Based Learning. Kluwer Academic Publishers, Boston/Dordrecht/London, 1993.
C. A. Atkeson. Using locally weighted regression for robot learning. In Proceedings of the 1991 IEEE International Conference on Robotics and Automation, pages 958–962, Sacramento, CA, April 1991.
J. Baxter. Learning Internal Representations. PhD thesis, Flinders University, Australia, 1995.
D. Beymer, A. Shashua, and T. Poggio. Example based image analysis and synthesis. A.I. Memo No. 1431, November 1993.
C.E. Brodley. Recursive Automatic Algorithm Selection for Inductive Learning. PhD thesis, University of Massachusetts, Amherst, MA 01003, August 1994. also available as COINS Technical Report 94-61.
J. Buhmann. Data clustering and learning. In M. Arbib, editor, Handbook of Brain Theory and Neural Networks, pages 278–282. Bradfort Books/MIT Press, 1995.
J. Buhmann, W. Burgard, A. B. Cremers, D. Fox, T. Hofmann, F. Schneider, J. Strikos, and S. Thrun. The mobile robot Rhino. AI Magazine, 16(1), 1995.
R. Caruana. Multitask learning: A knowledge-based of source of inductive bias. In P. E. Utgoff, editor, Proceedings of the Tenth International Conference on Machine Learning, pages 41–48, San Mateo, CA, 1993. Morgan Kaufmann.
R. Franke. Scattered data interpolation: Tests of some methods. Mathematics of Computation, 38(157): 181–200, January 1982.
J. H. Friedman. Flexible metric nearest neighbor classification. November 1994.
T. Hastie and R. Tibshirani. Discriminant adaptive nearest neighbor classification. Submitted for publication, December 1994.
H. Hild and A. Waibel. Multi-speaker/speaker-independent architectures for the multi-state time delay neural network. In Proceedings of the International Conference on Acoustics, Speech and Signal Processing, pages II 255–258. IEEE, April 1993.
M. Lando and S. Edelman. Generalizing from a single view in face recognition. Technical Report CS-TR 95-02, Department of Applied Mathematics and Computer Science, The Weizmann Institute of Science, Rehovot 76100, Israel, January 1995.
B. Mel. Seemore: A view-based approach to 3-d object recognition using multiple visual cues. In M.C. Mozer D.S. Touretzky and M.E. Hasselmo, editors, Advances in Neural Information Processing Systems 8. MIT Press, December 1996.
A. W. Moore. Efficient Memory-based Learning for Robot Control. PhD thesis, Trinity Hall, University of Cambridge, England, 1990.
A. W. Moore, D. J. Hill, and M. P. Johnson. An Empirical Investigation of Brute Force to choose Features, Smoothers and Function Approximators. In S. Hanson, S. Judd, and T. Petsche, editors, Computational Learning Theory and Natural Learning Systems, Volume 5. MIT Press, 1992.
H. P. Moravec. Sensor fusion in certainty grids for mobile robots. AI Magazine, pages 61–74, Summer 1988.
Y. Moses, S. Ullman, and S. Edelman. Generalization across changes in illumination and viewing position in upright and inverted faces. Technical Report CS-TR 93-14, Department of Applied Mathematics and Computer Science, The Weizmann Institute of Science, Rehovot 76100, Israel, 1993.
H. Murase and S. Nayar. Visual learning and recognition of 3-d objects from appearance. International Journal of Computer Vision, 14:5–24, 1994.
J. O’ Sullivan, T. M. Mitchell, and S. Thrun. Explanation-based neural network learning from mobile robot perception. In K. Ikeuchi and M. Veloso, editors, Symbolic Visual Learning. Oxford University Press, 1996.
J. O’ Sullivan and S. Thrun. A robot that improves its ability to learn. Internal Report, September 1995.
L. Y. Pratt. Transferring Previously Learned Back-Propagation Neural Networks to New Learning Tasks. PhD thesis, Rutgers University, Department of Computer Science, New Brunswick, NJ 08904, May 1993. also appeared as Technical Report ML-TR-37.
L. Rendell, R. Seshu, and D. Tcheng. Layered concept-learning and dynamically-variable bias management. In Proceedings of IJCAI-87, pages 308–314, 1987.
N. E. Sharkey and A. J. C. Sharkey. Adaptive generalization and the transfer of knowledge. In Proceedings of the Second Irish Neural Networks Conference, Belfast, 1992.
D. Silver and R. Mercer. Toward a model of consolidation: The retention and transfer of neural net task knowledge. In Proceedings of the INNS World Congress on Neural Networks, pages 164–169, Volume III, Washington, DC, July 1995.
C. Stanfill and D. Waltz. Towards memory-based reasoning. Communications of the ACM, 29(12): 1213–1228, December 1986.
S. C. Suddarth and A. Holden. Symbolic neural systems and the use of hints for developing complex systems. International Journal of Machine Studies, 35, 199
R. S. Sutton. Adapting bias by gradient descent: An incremental version of delta-bar-delta. In Proceeding of Tenth National Conference on Artificial Intelligence AAAI-92, pages 171–176, Menlo Park, CA, July 1992. AAAI, AAAI Press/The MIT Press.
S. Thrun. Exploration and model building in mobile robot domains. In E. Ruspini, editor, Proceedings of the ICNN-93, pages 175-180, San Francisco, CA, March 1993. IEEE Neural Network Council.
S. Thrun. Explanation-Based Neural Network Learning: A Lifelong Learning Approach. Kluwer Academic Publishers, Boston, MA, 1996.
S. Thrun. Is learning the n-th thing any easier than learning the first? In D. Touretzky, M. Mozer, and M.E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 640–646, Cambridge, MA, 1996. MIT Press.
S. Thrun and T. M. Mitchell. Learning one more thing. In Proceedings of ?CAI-95, Montreal, Canada, August 1995. IJCAI, Inc.
S. Thrun and J. O’Sullivan. Clustering learning tasks and the selective cross-task transfer of knowledge. Technical Report CMU-CS-95-209, Carnegie Mellon University, School of Computer Science, Pittsburgh, PA 15213, November 1995.
P. E. Utgoff. Machine Learning of Inductive Bias. Kluwer Academic Publishers, 1986
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer Science+Business Media New York
About this chapter
Cite this chapter
Thrun, S., O’Sullivan, J. (1998). Clustering Learning Tasks and the Selective Cross-Task Transfer of Knowledge. In: Thrun, S., Pratt, L. (eds) Learning to Learn. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-5529-2_10
Download citation
DOI: https://doi.org/10.1007/978-1-4615-5529-2_10
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7527-2
Online ISBN: 978-1-4615-5529-2
eBook Packages: Springer Book Archive