Abstract
Machine lifelong learning (ML3) is concerned with machines capable of learning and retaining knowledge over time, and exploiting this knowledge to assist new learning. An ML3 system must accurately retain knowledge of prior tasks while consolidating in knowledge of new tasks, overcoming the stability-plasticity problem. A system is presented using a context-sensitive multiple task learning (csMTL) neural network. csMTL uses a single output and additional context inputs for associating examples with tasks. A csMTL-based ML3 system is analyzed empirically using synthetic and real domains. The experiments focus on the effective retention and consolidation of task knowledge using both functional and representational transfer. The results indicate that combining the two methods of transfer serves best to retain prior knowledge, but at the cost of less effective new task consolidation.
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.
Similar content being viewed by others
References
Baxter, J.: Learning model bias. In: Touretzky, D.S., Mozer, M.C., Hasselmo, M.E. (eds.) Advances in Neural Information Processing Systems, vol. 8, pp. 169–175. The MIT Press, Cambridge (1996)
Caruana, R.A.: Multitask learning. Machine Learning 28, 41–75 (1997)
Fowler, B.: Context-Sensitive Multiple Task Learning with Consolidated Domain Knowledge. Master’s Thesis Thesis, Jodrey School of Computer Science, Acadia University (2011)
French, R.M.: Pseudo-recurrent connectionist networks: An approach to the sensitivity-stability dilemma. Connection Science 9(4), 353–379 (1997)
Grossberg, S.: Competitive learning: From interactive activation to adaptive resonance. Cognitive Science 11, 23–64 (1987)
Robins, A.V.: Catastrophic forgetting, rehearsal, and pseudorehearsal. Connection Science 7, 123–146 (1995)
Salakhutdinov, R., Adams, R., Tenenbaum, J., Ghahramani, Z., Griffiths, T.: Workshop: Transfer Learning Via Rich Generative Models. Neural Information Processing Systems (NIPS) (2010), http://www.mit.edu/~rsalakhu/workshop_nips2010/index.html
Silver, D.L., Mercer, R.E.: The parallel transfer of task knowledge using dynamic learning rates based on a measure of relatedness. Learning to Learn, 213–233 (1997)
Silver, D.L., Mercer, R.E.: The task rehearsal method of life-long learning: Overcoming impoverished data. In: Advances in Artificial Intelligence, 15th Conference of the Canadian Society for Computational Studies of Intelligence (AI 2002), pp. 90–101 (2002)
Silver, D.L., Poirier, R.: Sequential consolidation of learned task knowledge. In: 17th Conference of the Canadian Society for Computational Studies of Intelligence (AI 2004). LNAI, pp. 217–232 (2004)
Silver, D.L., Poirier, R., Currie, D.: Inductive tranfser with context-sensitive neural networks. Machine Learning 73(3), 313–336 (2008)
Thrun, S.: Is learning the n th thing any easier than learning the first? In: Advances in Neural Information Processing Systems 8, vol. 8, pp. 640–646 (1996)
Turney, P.D.: The identification of context-sensitive features: A formal definition of context for concept learning. In: 13th International Conference on Machine Learning (ICML 1996), Workshop on Learning in Context-Sensitive Domains, Bari, Italy, vol. NRC 39222, pp. 53–59 (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fowler, B., Silver, D.L. (2011). Consolidation Using Context-Sensitive Multiple Task Learning. In: Butz, C., Lingras, P. (eds) Advances in Artificial Intelligence. Canadian AI 2011. Lecture Notes in Computer Science(), vol 6657. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21043-3_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-21043-3_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21042-6
Online ISBN: 978-3-642-21043-3
eBook Packages: Computer ScienceComputer Science (R0)