Abstract
The selective transfer of task knowledge within the context of artificial neural networks is studied using a modified version of ηMTL (multiple task learning) previously reported. sMTL is a knowledge based inductive learning system that uses prior task knowledge and stochastic noise to adjust its inductive bias when learning a new task. The MTL representation of previously learned and consolidated tasks is used as the starting point for learning a new primary task. Task rehearsal ensures the stability of related secondary task knowledge within the sMTL network and stochastic noise is used to create plasticity in the network so as to allow the new task to be learned. sMTL controls the level of noise to each secondary task based on a measure of secondary to primary task relatedness. Experiments demonstrate that from impoverished training sets, sMTL uses the prior representations to quickly develop predictive models that have (1) superior generalization ability compared with models produced by single task learning or standard MTL and (2) equivalent generalization ability compared with models produced by ηMTL.
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
Yaser S. Abu-Mostafa. Hints. Neural Computation, 7:639–671, 1995.
A. Agarwal, R. J. Mammone, and D. K. Naik. An on-line training algorithm to overcome catastrophic forgetting. Intelligence Engineering Systems through Artificial Neural Networks, 2:239–244, 1992.
Jonathan Baxter. Learning internal representations. Proceedings of the Eighth International Conference on Computational Learning Theory, 1995.
Richard A. Caruana. Multitask learning. Machine Learning, 28:41–75, 1997.
S. E. Fahlman and C. Lebiere. The cascade-correlation learning architecture. Advances in Neural Information Processing Systems 2, 2:524–532, 1990. ed. D. S. Touretsky.
S. J. Hanson. A stochastic version of the delta rule. Physica D, 42:265–272, 1990.
J. Hertz, A. Krogh, and R. G. Palmer. Introduction to the Theory of Neural Computation. Adddison-Wesley Pub. Co., Redwood City, CA., 1991.
Thomas Heskes and Bert Kappen. On-line learning processes in artificial neural networks. In J. Taylor, editor, Mathematical Foundations of Neural Networks. Elsevier, Amsterdam, Netherlands, 1993.
L. Holmstrom and P. Koistinen. Using additive noise in back-propagation training. IEEE Transactions on Neural Networks, 3(1), 1992.
Anders Krogh and John Hertz. Generalization in a linear perceptron in the presence of noise. Journal of Physics, A(25):1135–1147, 1992.
K. Matsuoka. Noise injection into inputs in back-propagation learning. IEEE Transactions on Systems, Man and Cybernetics, 22(3):436–440, 1992.
Tom Mitchell and Sebastian Thrun. Explanation based neural network learning for robot control. Advances in Neural Information Processing Systems 5, 5: 287–294, 1993. ed. C. L. Giles and S. J. Hanson and J. D. Cowan.
Tom M. Mitchell. Machine Learning. McGraw Hill, New York, NY, 1997.
D. K. Naik and Richard J. Mammone. Learning by learning in neural networks. Artificial Neural Networks for Speech and Vision; ed. Richard J. Mammone, 1993.
Joseph O’Sullivan. Transfer of Learned Knowledge in Life-Long Learning Agents, A PhD Proposal. School of Computer Science, Carnegie Mellon University, February 1997.
Lorien Y. Pratt. Discriminability-based transfer between neural networks. Advances in Neural Information Processing Systems 5, 5:204–211, 1993. ed. C. L. Giles and S. J. Hanson and J.D. Cowan.
Mark Ring. Learning sequential tasks by incrementally adding higher orders. Advances in Neural Information Processing Systems 5, 5:155–122, 1993. ed. C. L. Giles and S. J. Hanson and J. D. Cowan.
Anthony V. Robins. Catastrophic forgetting, rehearsal, and pseudorehearsal. Connection Science, 7: 123–146, 1995.
Noel E. Sharkey and Amanda J. C. Sharkey. Adaptive generalization and the transfer of knowledge. Working paper-Center for Connection Science, 1992.
Jude W. Shavlik and Geoffrey G. Towell. An appraoch to combining explanation based and neural learning algorithms. Readings in Machine Learning, pages 828–839, 1990. ed. Jude W. Shavlik and Thomas G. Dietterich.
Daniel L. Silver. Selective Transfer of Neural Network Task Knowledge. PhD Thesis, Dept. of Computer Science, University of Western Ontario, London, Canada, June 2000.
Daniel L. Silver and Robert E. Mercer. The parallel transfer of task knowledge using dynamic learning rates based on a measure of relatedness. Connection Science Special Issue: Transfer in Inductive Systems, 8(2): 277–294, 1996.
Daniel L. Silver and Robert E. Mercer. The task rehearsal method of life-long learning: Overcoming impoverished data. Advances in Artificial Intelligence, 15th Conference of the Canadian Society for Computational Studies of Intelligence (CAI2002), 2338:90–101, 2002.
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. Lifelong learning algorithms. Learning to Learn, pages 181–209, 1997.
Paul E. Utgo. Machine Learning of Inductive Bias. Kluwer Academc Publisher, Boston, MA, 1986.
Alexander Waibel, Hidefumi Sawai, and Kiyoshiro Shikano. Modularity and scaling in large phonemic neural networks. IEEE Transactions on Acoustics, Speech, and Signal Processing, 37(12):1888–1898, December 1989.
C. Wang and J. C. Principe. Training neural networks with additive noise in the desired signal. IEEE-NN, 10(6):1511, November 1999.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Silver, D.L., McCracken, P. (2003). Selective Transfer of Task Knowledge Using Stochastic Noise. In: Xiang, Y., Chaib-draa, B. (eds) Advances in Artificial Intelligence. Canadian AI 2003. Lecture Notes in Computer Science, vol 2671. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44886-1_16
Download citation
DOI: https://doi.org/10.1007/3-540-44886-1_16
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40300-5
Online ISBN: 978-3-540-44886-0
eBook Packages: Springer Book Archive