S. J. Wan, S. K. M. Wong. "A Measure for Concept Dissimilarity and Its Applications in Machine Learning." Proceedings of the International Conference on Computing and Information. pp. 267-273. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
A Statistical Approach to 3D Object Detection Applied to Faces .. - Schneiderman (2000) (17 citations) (Correct)
....corresponding influence images for several profile faces. 7.3. Analysis of Pair wise Statistical Dependency We also evaluated pair wise statistical dependency among wavelet coefficients for both frontal and right profile view. We evaluated pair wise dependency using the following measure [64][85][86] 69 (41) where c i and c j represent two wavelet coefficient that are discretized to take on m values, v k . Below we show some dependency images for individual coefficients. These images show the measure of pair wise statistical dependency between a single coefficient and the rest ....
....Figure 48. Influence images for various car inputs 75 8.3. Analysis of Pair wise Statistical Dependency We also evaluated pair wise statistical dependency among wavelet coefficients for both frontal and right profile view. We evaluated pair wise dependency using the following measure [64][85][86] 42) where c i and c j represent two wavelet coefficient that are discretized to take on m values, v k . Below we show some dependency images for individual coefficients. These images show the measure of statistical dependency between a single coefficient and the rest of the coefficients. ....
S. J. Wan, S. K. M. Wong. "A Measure for Concept Dissimilarity and Its Applications in Machine Learning." Proceedings of the International Conference on Computing and Information. pp. 267-273.
On the Optimality of the Simple Bayesian Classifier under.. - Pazzani (1997) (107 citations) (Correct)
....in the data. However, a first and feasible approach consists in measuring pairwise dependencies (i.e. dependencies between pairs of attributes given the class) Given attributes Am and A n and the class variable C, a possible measure of the degree of pairwise dependence between Am and A n given C (Wan Wong, 1989; Kononenko, 1991) is D(Am,A n C) H(A m C) H(A n C) H(A mA n C) 4) where AmA n represents the Cartesian product of attributes Am and A n (i.e. a derived attribute with one possible value corresponding to each combination of values of Am and A n ) and for all classes i and ....
....present is that detecting these is not necessarily the best way to improve performance. This section empirically tests this claim by comparing Pazzani s (1996) extension with one that differs from it solely by using the method for attribute dependence detection described in (Kononenko, 1991) and (Wan Wong, 1989). In each case, the algorithm finds the single best pair of attributes to join by considering all possible joins. Two measures for determining the best pair were compared. Following Pazzani (1996) the first measure was estimated accuracy, as determined by leave one out cross validation on the ....
Wan, S. J., &Wong, S. K. M. (1989). A measure for concept dissimilarity and its applications in machine learning. Proceedings of the International Conference on Computing and Information (pp. 267--273). Toronto, Ontario: North-Holland.
On the Optimality of the Simple Bayesian Classifier under.. - Domingos, Pazzani (1997) (107 citations) (Correct)
....in the data. However, a first and feasible approach consists in measuring pairwise dependencies (i.e. dependencies between pairs of attributes given the class) Given attributes Am and An and the class variable C, a possible measure of the degree of pairwise dependence between Am and An given C (Wan Wong, 1989; Kononenko, 1991) is D(Am ; An jC) H(Am jC) H(An jC) Gamma H(AmAn jC) 4) where AmAn represents the Cartesian product of attributes Am and An (i.e. a derived attribute with one possible value corresponding to each combination of values of Am and An ) and for all classes i and attribute ....
....present is that detecting these is not necessarily the best way to improve performance. This section empirically tests this claim by comparing Pazzani s (1996) extension with one that differs from it solely by using the method for attribute dependence detection described in (Kononenko, 1991) and (Wan Wong, 1989). In each case, the algorithm finds the single best pair of attributes to join by considering all possible joins. Two measures for determining the best pair were compared. Following Pazzani (1996) the first measure was estimated accuracy, as determined by leave one out cross validation on the ....
Wan, S. J., & Wong, S. K. M. (1989). A measure for concept dissimilarity and its applications in machine learning. Proceedings of the International Conference on Computing and Information (pp. 267--273). Toronto, Ontario: North-Holland.
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