Active Learning of the Generalized High-Low-Game

Hasenjäger M, Ritter H (1996)
In: Artificial Neural Networks — ICANN 96: 1996 International Conference Bochum, Germany, July 16–19, 1996 Proceedings. Malsburg von der C, Seelen von W, Vorbrüggen J, Sendhoff B (Eds); Lecture Notes in Computer Science, 1112. Berlin: Springer: 501-506.

Conference Paper | Published | English

No fulltext has been uploaded

Author
;
Editor
Malsburg von der, Christoph ; Seelen von, Werner ; Vorbrüggen, J. ; Sendhoff, Bernhard
Abstract
In this paper, we study the performance of active learning with the query algorithm Query by Committee (QBC), which selects a new query such that it approximately maximizes the expected information gain. As target functions, we introduce a generalization of the High-Low-Game, for which we derive a theoretically optimal query sequence. This allows us to compare the performance of a QBC-learner with an information-optimal active learner. Simulations show that an active learner that selects queries with QBC rapidly converges against a learner trained with theoretically optimal queries.
Publishing Year
Conference
ICANN 96
Location
Bochum
Conference Date
1996-07-16 – 1996-07-19
PUB-ID

Cite this

Hasenjäger M, Ritter H. Active Learning of the Generalized High-Low-Game. In: Malsburg von der C, Seelen von W, Vorbrüggen J, Sendhoff B, eds. Artificial Neural Networks — ICANN 96: 1996 International Conference Bochum, Germany, July 16–19, 1996 Proceedings. Lecture Notes in Computer Science. Vol 1112. Berlin: Springer; 1996: 501-506.
Hasenjäger, M., & Ritter, H. (1996). Active Learning of the Generalized High-Low-Game. In C. Malsburg von der, W. Seelen von, J. Vorbrüggen, & B. Sendhoff (Eds.), Lecture Notes in Computer Science: Vol. 1112. Artificial Neural Networks — ICANN 96: 1996 International Conference Bochum, Germany, July 16–19, 1996 Proceedings (pp. 501-506). Berlin: Springer.
Hasenjäger, M., and Ritter, H. (1996). “Active Learning of the Generalized High-Low-Game” in Artificial Neural Networks — ICANN 96: 1996 International Conference Bochum, Germany, July 16–19, 1996 Proceedings, ed. C. Malsburg von der, W. Seelen von, J. Vorbrüggen, and B. Sendhoff Lecture Notes in Computer Science, vol. 1112, (Berlin: Springer), 501-506.
Hasenjäger, M., & Ritter, H., 1996. Active Learning of the Generalized High-Low-Game. In C. Malsburg von der, et al., eds. Artificial Neural Networks — ICANN 96: 1996 International Conference Bochum, Germany, July 16–19, 1996 Proceedings. Lecture Notes in Computer Science. no.1112 Berlin: Springer, pp. 501-506.
M. Hasenjäger and H. Ritter, “Active Learning of the Generalized High-Low-Game”, Artificial Neural Networks — ICANN 96: 1996 International Conference Bochum, Germany, July 16–19, 1996 Proceedings, C. Malsburg von der, et al., eds., Lecture Notes in Computer Science, vol. 1112, Berlin: Springer, 1996, pp.501-506.
Hasenjäger, M., Ritter, H.: Active Learning of the Generalized High-Low-Game. In: Malsburg von der, C., Seelen von, W., Vorbrüggen, J., and Sendhoff, B. (eds.) Artificial Neural Networks — ICANN 96: 1996 International Conference Bochum, Germany, July 16–19, 1996 Proceedings. Lecture Notes in Computer Science. 1112, p. 501-506. Springer, Berlin (1996).
Hasenjäger, Martina, and Ritter, Helge. “Active Learning of the Generalized High-Low-Game”. Artificial Neural Networks — ICANN 96: 1996 International Conference Bochum, Germany, July 16–19, 1996 Proceedings. Ed. Christoph Malsburg von der, Werner Seelen von, J. Vorbrüggen, and Bernhard Sendhoff. Berlin: Springer, 1996.Vol. 1112. Lecture Notes in Computer Science. 501-506.
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