P. Kontkanen, P. Myllymaki, T. Silander, H. Tirri, and P. Grunwald. On predictive distributions and Bayesian networks. In W. Daelemans, P. Flach, and A. van den Bosch, editors, Proceedings of the Seventh Belgian-Dutch Conference on Machine Learning (BeNeLearn'97), pages 59--68, Tilburg, the Netherlands, October 1997. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
On the Accuracy of Stochastic Complexity Approximations - Kontkanen, Myllymäki.. (1999) Self-citation (Kontkanen Myllymaki Silander Tirri) (Correct)
No context found.
P. Kontkanen, P. Myllymaki, T. Silander, H. Tirri, and P. Grunwald. On predictive distributions and Bayesian networks. In W. Daelemans, P. Flach, and A. van den Bosch, editors, Proceedings of the Seventh Belgian-Dutch Conference on Machine Learning (BeNeLearn'97), pages 59--68, Tilburg, the Netherlands, October 1997.
On Supervised Learning of Bayesian Network Parameters - Wettig, Grünwald, Roos.. (2002) Self-citation (Myllymaki Tirri Grunwald) (Correct)
No context found.
Kontkanen, P., Myllymaki, P., Silander, T., Tirri, H., & Grunwald, P. 2000. On Predictive Distributions and Bayesian Networks. Statistics and Computing, 10, 39--54.
BAYDA: Software for Bayesian Classification and.. - Kontkanen.. (1998) (2 citations) Self-citation (Kontkanen Silander Tirri) (Correct)
No context found.
Kontkanen, P.; Myllymaki, P.; Silander, T.; Tirri, H.; and Grunwald, P. 1997c. On predictive distributions and Bayesian networks. In Daelemans, W.; Flach, P.; and van den Bosch, A., eds., Proceedings of the Seventh Belgian-Dutch Conference on Machine Learning (BeNeLearn'97), 59--68.
Bayes Optimal Instance-Based Learning - Kontkanen, Myllymäki, al. (1998) (2 citations) Self-citation (Kontkanen Myllymaki Silander Tirri) (Correct)
....by summing the individual predictions weighted by the model class probabilities P (M k j D;M) As a matter of fact, from the probability theory point of view the Bayesian instance based learning predictive distribution (4) produces optimally accurate predictions within the chosen model family. In [17, 18], we described how the recently published new coding scheme by Rissanen [28] for representing the stochastic complexity measure [27] offers an alternative definition for an optimal predictive distribution. This definition can be justified by information theoretic arguments, but this approach will ....
....much more conservative than the single model MLNB. For small samples it is well known that the traditional MLNB classifier is too dependent on the observed data and does not take into account that future data may turn out to be different. A more detailed discussion on this topic can be found in [17, 18]. 5 Conclusion In this paper we proposed a Bayesian framework for defining the instance based learning approach. The framework is based on the observation that moving from a model based learning approach, such as decision tree learning, to an instancebased learning approach that relies solely on ....
P. Kontkanen, P. Myllymaki, T. Silander, H. Tirri, and P. Grunwald. On predictive distributions and Bayesian networks. In W. Daelemans, P. Flach, and A. van den Bosch, editors, Proceedings of the Seventh Belgian-Dutch Conference on Machine Learning (BeNeLearn'97), pages 59--68, Tilburg, the Netherlands, October 1997. 88
Quantitatively Tight Sample Complexity Bounds - Langford (2002) (Correct)
No context found.
P.Kontkanen, P. Myllymaki, T. Silander, H.Tirri, and P. Grunwald, Predictive Distributions and Bayesian Networks, Journal of Statistics and Computing 10, pp. 39-54, 2000.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC