Generalization Abilities of Cascade Network Architectures

Littmann E, Ritter H (1993)
In: Advances in Neural Information Processing Systems. Hanson SJ (Ed);5. San Mateo: Kaufman.

Conference Paper | Published | English

No fulltext has been uploaded

Author
;
Editor
Hanson, Stephen Jose
Abstract
In [5], a new incremental cascade network architecture has been presented. This paper discusses the properties of such cascade networks and investigates their generalization abilities under the particular constraint of small data sets. The evaluation is done for cascade networks consisting of local linear maps using the MackeyGlass time series prediction task as a benchmark. Our results indicate that to bring the potential of large networks to bear on the problem of extracting information from small data sets without running the risk of overfitting , deeply cascaded network architectures are more favorable than shallow broad architectures that contain the same number of nodes. 1 Introduction For many real-world applications, a major constraint for the successful learning from examples is the limited number of examples available. Thus, methods are required, that can learn from small data sets. This constraint makes the problem of generalization particularly hard. If the number of adjus...
Publishing Year
Conference
NIPS 92
Location
Denver
PUB-ID

Cite this

Littmann E, Ritter H. Generalization Abilities of Cascade Network Architectures. In: Hanson SJ, ed. Advances in Neural Information Processing Systems. Vol 5. San Mateo: Kaufman; 1993.
Littmann, E., & Ritter, H. (1993). Generalization Abilities of Cascade Network Architectures. In S. J. Hanson (Ed.), Advances in Neural Information Processing Systems (Vol. 5). San Mateo: Kaufman.
Littmann, E., and Ritter, H. (1993). “Generalization Abilities of Cascade Network Architectures” in Advances in Neural Information Processing Systems, ed. S. J. Hanson, vol. 5, (San Mateo: Kaufman).
Littmann, E., & Ritter, H., 1993. Generalization Abilities of Cascade Network Architectures. In S. J. Hanson, ed. Advances in Neural Information Processing Systems. no.5 San Mateo: Kaufman.
E. Littmann and H. Ritter, “Generalization Abilities of Cascade Network Architectures”, Advances in Neural Information Processing Systems, S.J. Hanson, ed., vol. 5, San Mateo: Kaufman, 1993.
Littmann, E., Ritter, H.: Generalization Abilities of Cascade Network Architectures. In: Hanson, S.J. (ed.) Advances in Neural Information Processing Systems. 5, Kaufman, San Mateo (1993).
Littmann, Enno, and Ritter, Helge. “Generalization Abilities of Cascade Network Architectures”. Advances in Neural Information Processing Systems. Ed. Stephen Jose Hanson. San Mateo: Kaufman, 1993.Vol. 5.
This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar
ISBN Search