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.
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Littmann, Enno;
Ritter, HelgeUniBi ![](https://pub.uni-bielefeld.de/images/icon_orcid.png)
![](https://pub.uni-bielefeld.de/images/icon_orcid.png)
Herausgeber*in
Hanson, Stephen Jose
Einrichtung
Abstract / Bemerkung
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...
Erscheinungsjahr
1993
Titel des Konferenzbandes
Advances in Neural Information Processing Systems
Band
5
Konferenz
NIPS 92
Konferenzort
Denver
ISBN
1-55860-274-7
Page URI
https://pub.uni-bielefeld.de/record/2715304
Zitieren
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, Enno, and Ritter, Helge. 1993. “Generalization Abilities of Cascade Network Architectures”. In Advances in Neural Information Processing Systems, ed. Stephen Jose Hanson. Vol. 5. San Mateo: Kaufman.
Littmann, E., and Ritter, H. (1993). “Generalization Abilities of Cascade Network Architectures” in Advances in Neural Information Processing Systems, Hanson, S. J. ed., 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.