Abstract
With a distinction made between two forms of task knowledge transfer, representational and functional, ηMTL, a modified version of the MTL method of functional (parallel) transfer, is introduced. The ηMTL method employs a separate learning rate, η k , for each task output node k, η k varies as a function of a measure of relatedness, R k , between the th task and the primary task of interest. Results of experiments demonstrate the ability of ηMTL to dynamically select the most related source task(s) for the functional transfer of prior domain knowledge. The ηMTL method of learning is nearly equivalent to standard MTL when all parallel tasks are sufficiently related to the primary task, and is similar to single task learning when none of the parallel tasks are related to the primary task.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Yaser S. Abu-Mostafa, Hints, Neural Computation, Massachusetts Institute of Technology, Vol. 7, pp. 639–671, 1995.
Jonathan Baxter, Learning internal representations, Proceedings of the Eighth International Conference on Computational Learning Theory, (to appear) ACM Press, Santa Cruz, CA, 1995.
Jonathan Baxter, Learning Internal Representations, Phd Thesis, Department of Mathematics and Staistics, The Flinders University of South Australia, Australia, 1995.
Richard A. Caruana, Multitask Learning: A Knowledge-Based Source of Inductive Bias, Proceedings of the tenth international conference on machine learning, University of Massachusetts, pp. 41–48, June 1993.
Richard A. Caruana, Learning many related tasks at the same time with backpropagation, Advances in Neural information Processing Systems 7, Morgan Kaufmann, Vol. 7, pp. 657–664, San Mateo, CA, 1995.
H. Ellis, Transfer of Learning, MacMillan, New York, NY, 1965.
S.E. Fahlman and C. Lebiere, The cascade-correlation learning architecture, Advances in Neural Information Processing Systems 2, Morgan Kaufmann, Vol. 2, pp. 524–532, San Mateo, CA, 199
Rogers P. Hall, Computational approaches to analogical reasoning: A comparative analysis, Arificial Intelligence, Elseivier Sience Publishers B.V., Vol. 39, pp. 39–120, North-Holland, 1989.
The Math Works Inc, The Student Edition of MATLAB, Version 4, Users Guide, Prentice Hall, Englewood Cliffs, NJ, 1995.
R.A. Jacobs, Increased rates of convergence through learning rate adaptation, Neural Networks, Vol. 1, pp. 295–307, 1988.
E. James Kehoe, A layered network model of associative learning: Learning to learn and configuration, Psychological Review, Vol. 95, No. 4, pp. 411–433, 1988.
Tom. M. Mitchell, The need for biases in learning generalizations, Readings in Machine Learning, Morgan Kaufmann, pp. 184–191, San Mateo, CA, 1980.
Tom Mitchell and Sebastian Thrun, Explanation based neural network learning for robot control, Advances in Neural Information Processing Systems 5, Morgan Kaufmann, Vol. 5, pp. 287–294, San Mateo, CA, 1993.
D. K. Naik, R. J. Mammone, and A. Agarwal, Meta-Neural Network approach to learning by learning, Intelligence Engineering Systems through Artificial Neural Networks, ASME Press, Vol. 2, pp. 245–252, 1992.
D.K. Naik and Richard J. Mammone, Learning by learning in neural networks, Artificial Neural Networks for Speech and Vision; ed: Richard J. Mammone, Chapman and Hall, London, 19
Lorien Y. Pratt, Discriminability-Based transfer between neural networks, Advances in Neural Information Processing Systems 5, Morgan Kaufmann, Vol. 5, pp. 204–211, San Mateo, CA, 199
Lorien Y. Pratt, Transferring previously learned back-propagation neural networks to new learning tasks, PhD Thesis, Department of Computer Science, Rutgers University, New Brunswick, NJ, 1993.
Lorien Y. Pratt, Experiments on the transfer of knowledge between neural networks, In S. Hanson, G. Drastal, and R. Rivest, editors, Computational Learning Theory and Natural Learning Systems, Constraints and Prospects, MIT Press, pp. 523–560, Cambridge, Mass., 1994.
Mark Ring, Learning sequential tasks by incrementally adding higher orders, Advances in Neural Information Processing Systems 5, Morgan Kaufmann, Vol. 5, pp. 155–222, San Mateo, CA, 1993.
Noel E. Sharkey and Amanda J.C. Sharkey, Adaptive generalization and the transfer of knowledge, Working paper-Center for Connection Science, University of Exeter, pp. n.sharkey@dcs.shef.ac.uk, UK, 1992.
Jude W. Shavlik and Geoffrey G. Towell, An appraoch to combining explanation-based and neural learning algorithms, Readings in Machine Learning, Morgan Kaufmann, pp. 828–839, San Mateo, CA, 1990.
Daniel L. Silver and Robert E. Mercer, Toward a model of consolidation: The retention and transfer of neural net task knowledge, Proceedings of the INNS World Congress on Neural Networks, Lawrence Erlbaun Assosciates, Vol. III, pp. 164–169, July 1995.
Satinder P. Singh, Transfer of learning by composing solutions for elemental sequential tasks, Machine Learning, 1992.
Steven Suddarth and Y Kergoisien, Rule injection hints as a means of improving network performance and learning time, Proceedings of the EURASIP workshop on Neural Networks, 1990.
Sebastian Thrun and Tom M. Mitchell, Lifelong Robot Learning, Technical Report IAI-TR-93-7, Institute for Informatics III, University of Bonn, Bonn, Germany, July 1993.
Sebastian Thrun, A Lifelong Learning Perspective for Mobile Robot Control, Proceedings of the IEEE Conference on Intelligent Robots and Systems, IEEE, September 12-16, 1994.
Sebastian Thrun and Tom M. Mitchell, Learning one more thing, Technical Report CMU-CS-94-184, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, 1994.
Geoffrey G. Towell, Jude W. Shavlik, and Michiel O. Noordewier, Refinement of approximate domain theories by knowledge-based neural networks, Proceedings Eigth National Conference on Artificial Intelligence (AAAI-90), AAAI Press/MIT Press, Vol. 2, pp. 861–866,Menlo Park, CA, 1990.
T.P. Vogl, J.K. Mangis, A.K. Rigler, W.T. Zink, and D.L. Alkon, Accelerating the convergence of the back-propagation method, Biological Cybernetics, Vol. 59, pp. 257–263, 1988.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
� 1996 Springer Science+Business Media New York
About this chapter
Cite this chapter
Silver, D.L., Mercer, R.E. (1996). The Parallel Transfer of Task Knowledge Using Dynamic Learning Rates Based on a Measure of Relatedness. In: Thrun, S., Pratt, L. (eds) Learning to Learn. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-5529-2_9
Download citation
DOI: https://doi.org/10.1007/978-1-4615-5529-2_9
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7527-2
Online ISBN: 978-1-4615-5529-2
eBook Packages: Springer Book Archive