Abstract
A massive amount of data is being produced in a continual stream, in real time, which renders traditional batch processing based data mining and neural network techniques as incapable. In this paper we focus on transfer learning from Spike Train Data, for which traditional techniques often require tasks to be distinctively identified during the training phase. We propose a novel dual network model that demonstrates transfer learning from spike train data without explicit task specification. An implementation of the proposed approach was tested experimentally to evaluate its ability to use previously learned knowledge to improve the learning of new tasks.
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
References
Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, vol. 2, pp. 524–532, Denver 1989. Morgan Kaufmann, San Mateo (1990)
Geramifard, A., Doshi, F., Redding, J., Roy, N., How, J.: Online discovery of feature dependencies. In: Proceedings of the 28th International Conference on Machine Learning (ICML 2011), pp. 881–888 (2011)
Kohonen, T.: Self-organized formation of topologically correct feature maps. Biol. Cybern. 43(1), 59–69 (1982)
Maass, W.: Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10(9), 1659–1671 (1997)
Mitchell, T.: The need for biases in learning generalizations. In: Readings in Machine Learning, pp. 184–191 (1980)
Pratt, L., Jennings, B.: A survey of transfer between connectionist networks. Connection Sci. 8(2), 163–184 (1996)
Pratt, L.Y.: Discriminability-based transfer between neural networks. In: Advances in Neural Information Processing Systems 5, [NIPS Conference], pp. 204–211. Morgan Kaufmann Publishers Inc., San Francisco (1993)
Pratt, L.Y.: Transferring previously learned back-propagation neural networks to new learning tasks. Ph.D. thesis, Rutgers University, Department of Computer Science (1993)
Pratt, L.Y., Mostow, J., Kamm, C.A.: Direct transfer of learned information among neural networks. In: Proceedings of the Ninth National Conference on Artificial Intelligence, AAAI 1991, vol. 2, pp. 584–589. AAAI Press (1991)
Shultz, T.R., Rivest, F.: Knowledge-based cascade-correlation: using knowledge to speed learning. Connection Sci. 13(1), 43–72 (2001)
Silver, D.L.: Selective transfer of neural network task knowledge. Ph.D. thesis, The University of Western Ontario, AAINQ58190 (2000)
Waibel, A., Sawai, H., Shikano, K.: Modularity and scaling in large phonemic neural networks. IEEE Trans. Acoust. Speech Signal Process. 37(12), 1888–1898 (1989)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Johnson, K., Liu, W. (2015). A Dual Network for Transfer Learning with Spike Train Data. In: Pfahringer, B., Renz, J. (eds) AI 2015: Advances in Artificial Intelligence. AI 2015. Lecture Notes in Computer Science(), vol 9457. Springer, Cham. https://doi.org/10.1007/978-3-319-26350-2_25
Download citation
DOI: https://doi.org/10.1007/978-3-319-26350-2_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26349-6
Online ISBN: 978-3-319-26350-2
eBook Packages: Computer ScienceComputer Science (R0)