The Parallel Transfer of Task Knowledge Using Dynamic Learning Rates Based on a Measure of Relatedness

Connection Science

Volumn 8, Issue 2, 1996, Pages 277-294

  Silver, Daniel L ^a   Mercer, Robert E ^a  

^a UNIVERSITY OF WESTERN ONTARIO   (Canada)

Author keywords

Artificial neural networks; Knowledge based inductive bias; Learning to learn; Parallel learning; Task knowledge transfer; Task relatedness

Indexed keywords

EID: 0030491431     PISSN: 09540091     EISSN: None     Source Type: Journal    
DOI: 10.1080/095400996116929     Document Type: Article

References (29)

1. Abu-Mostafa, Y.S. (1995) Hints. In Neural Computation, Vol. 7. Cambridge, MA: MIT Press, pp. 639-671.
2. Baxter, J. (1995a) Learning internal representations. Proceedings of the 8th International Conference on Computational Learning Theory. Santa Cruz, CA: ACM Press (to appear).
3. Baxter, J. (1995b) Learning internal representations, PhD Thesis, Department of Mathematics and Statistics. The Flinders University of South Australia.
4. Caruana, R.A. (1993) Multitask learning: A knowledge-based source of inductive bias. Proceedings of the 10th International Conference on Machine Learning. University of Massachusetts, pp. 41-48.
5. Caruana, R.A. (1995) Learning many related tasks at the same time with backpropagation. Advances in Neural Information Processing Systems, Vol. 7. San Mateo, CA: Morgan Kaufmann, pp. 657-664.
6. Ellis, H. (1965) Transfer of Learning. New York: Macmillan.
7. Fahlman, S.E. & Lebiere, C. (1990) The cascade-correlation learning architecture. Advances in Neural Information Processing Systems, Vol. 2. San Mateo, CA: Morgan Kaufmann, pp. 524-532.
8. Hall, R.P. (1989) Computational approaches to analogical reasoning: A comparative analysis. Artificial Intelligence, 39, 39-120.
9. Jacobs, R.A. (1988) Increased rates of convergence through learning rate adaptation. Neural Networks, 1, 295-307.
10. Kehoe, E.J. (1988) A layered network model of associative learning: Learning to learn and configuration. Psychological Review, 95, 411-433.
11. MathWorks Inc. (1995) The Student Edition of MATLAB, Version 4, Users Guide. Englewood Cliffs, NJ: Prentice-Hall.
12. Mitchell, T.M. (1980) The need for biases in learning generalizations. In Readings in Machine Learning. San Mateo, CA: Morgan Kaufmann, pp. 184-191.
13. Mitchell, T. & Thrun, S. (1993) Explanation based neural network learning for robot control. Advances in Neural Information Processing Systems. San Mateo, CA: Morgan Kaufmann, pp. 287-294.
14. Naik, D.K. & Mammone, R.J. (1993) Learning by learning in neural networks. In R.J. Mammone (Ed.), Artificial Neural Networks for Speech and Vision. London: Chapman and Hall.
15. Naik, D.K., Mammone, R.J. & Agarwal, A. (1992) Meta-neural network approach to learning by learning. Intelligence Engineering Systems through Artificial Neural Networks, 2, 245-252.
16. Pratt, L.Y. (1993a) Discriminability-based transfer between neural networks. Advances in Neural Information Processing Systems, Vol. 5. San Mateo, CA: Morgan Kaufmann, pp. 204-211.
17. Pratt, L.Y. (1993b) Transferring previously learned back-propagation neural networks to new learning tasks, PhD Thesis, Department of Computer Science, Rutgers University, New Brunswick, NJ.
18. Pratt, L.Y. (1994) Experiments on the transfer of knowledge between neural networks. In S. Hanson, G. Drastal & R. Rivest (Eds), Computational Learning Theory and Natural Learning Systems, Constraints and Prospects. Cambridge, MA: MIT Press, pp. 523-560.
19. Ring, M. (1993) Learning sequential tasks by incrementally adding higher orders. Advances in Neural Information Processing Systems, Vol. 5. San Mateo, CA: Morgan Kaufmann, pp. 155-162.
20. Sharkey, N.B. & Sharkey, A.J.C. (1992) Adaptive generalization and the transfer of knowledge, Working Paper, Center for Connection Science, University of Exeter, UK.
21. Shavlik, J.W. & Towell, G.G. (1990) An approach to combining explanation-based and neural learning algorithms. Readings in Machine Learning. San Mateo, CA: Morgan Kaufmann, pp. 828-839.
22. Silver, D.L. & Mercer, R.E. (1995) Towards a model of consolidation: The retention and transfer of neural net task knowledge. Proceedings of the INNS World Congress on Neural Networks, Vol. III. Hillsdale, NJ: Lawrence Erlbaum, pp. 164-169.
23. Singh, S.P. (1992) Transfer of learning by composing solutions for elemental sequential tasks, Machine Learning.
24. Suddarth, S. & Kergoisien, Y. (1990) Rule injection hints as a means of improving network performance and learning time, Proceedings of the EURASIP Workshop on Neural Networks.
25. Thrun, S. (1994) A lifelong learning perspective for mobile robot control. Proceedings of the IEEE Conference on Intelligent Robots and Systems, IEEE, September.
26. Thrun, S. & Mitchell, T.M. (1993) Lifelong robot learning, Technical Report IAI-TR-93-7, Institute for Informatics III, University of Bonn, Bonn, Germany.
27. Thrun, S. & Mitchell, T.M. (1994) Learning one more thing, Technical Report CMU-CS-94-184, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA.
28. Towell, G.G., Shavlik, J.W. & Noordewier, M.O. (1990) Refinement of approximate domain theories by knowledge-based neural networks. Proceedings 8th National Conference on Artificial Intelligence (AAAI-90), Vol. 2. Menlo Park, CA: AAAI Press/MIT Press, pp. 861-866.
29. Vogl, T.P., Mangis, J.K., Rigler, A.K., Zink, W.T. & Alkon, D.L. (1988) Accelerating the convergence of the back-propagation method. Biological Cybernetics, 59, 257-263.