Christoper J. Merz and Michael J. Pazzani. A principal components approach to combining regression estimates. Machine Learning, 36(1-2):9{ 32, 1999.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....are included in meta classifiers. A detailed account on the similarities and di#erences between several meta learning methods. The analysis examines and contrasts the applicability of the pruning methods on a number of existing techniques for combining classifiers (majority voting, SCANN [ Merz, 1999 ] A systematic approach for bridging databases with di#erent schemata and for combining incompatible classification models. The application of JAM on the real world learning task of fraud detection in financial information systems and the evaluation of their performance under three ....

....functions to arbitrate among the predictions generated by the classifiers [ Chan Stolfo, 1993b; Jacobs et al. 1991; Jordan Xu, 1993; R. J. 1994; Jordan Jacobs, 1994; Kong Dietterich, 1995; Ortega, Koppel, Argamon Engelson, 1999 ] methods that rely on principal components analysis [ Merz, 1999; Merz Pazzani, 1999 ] or methods that apply inductive learning techniques to learn the behavior and properties of the candidate classifiers [ Wolpert, 1992; Chan Stolfo, 1993b ] In this thesis, we describe a distributed meta learning system that supports, in principle, any of these ....

[Article contains additional citation context not shown here]

Merz, C., and Pazzani, M. 1999. A principal components approach to combining regression estimates. Machine Learning. In press.

....to discover the correlations among the available models. Meta learning has the advantage of employing an arbitrary learning algorithm for computing non linear relations 12 among the classifiers (at the expense, perhaps, of generating less intuitive representations) Merz and Pazzani s PCR # [22] and Merz s SCANN [21] algorithms are also algorithms that combine multiple models, the first for improving regression estimates, the latter for improving classification performance. The PCR # algorithm maps the estimates of the models into a new representation using principal components analysis ....

C. Merz and M. Pazzani. A principal components approach to combining regression estimates. Machine Learning, 1998. to appear.

....using two ensemble learning techniques, namely Bagging and Arcing. The ensemble learning literature considers different ways to compute the output of the ensemble. Averaging the outputs of the individual models with uniform weight is probably the simplest possibility. Perrone and Cooper [19][17] refer to this method as Basic Ensemble Method (BEM) or naive Bagging. Breiman proposed an Arcing method Arc fx [2] 3] for mining from large data set and stream data . It is fundamentally based on the idea of Arcing adaptive re sampling by giving higher weights to those instances that are ....

C. J. Merz and M. J. Pazzani. A principal components approach to combining regression estimates. Machine Learning, 36(1--2):9--32, 1999.

....to arbitrate among the predictions generated by the classifiers, Jacobs, Jordan, Nowlan and Hinton, 1991; Jordan and Jacobs, 1994; Jordan and Xu, 1993; Kong and Dietterich, 1995; Ortega, Koppel and Argamon Engelson, 1999; R. and J. 1994) methods that rely on principal components analysis (Merz, 1999; Merz and Pazzani, 1999) or methods that apply inductive learning techniques to learn the behavior and properties of the candidate classifiers (Chan and Stolfo, 1993; Wolpert, 1992) Constructing ensembles of classifiers is not cheap and produces a final outcome that is expensive due to the ....

....among the predictions generated by the classifiers, Jacobs, Jordan, Nowlan and Hinton, 1991; Jordan and Jacobs, 1994; Jordan and Xu, 1993; Kong and Dietterich, 1995; Ortega, Koppel and Argamon Engelson, 1999; R. and J. 1994) methods that rely on principal components analysis (Merz, 1999; Merz and Pazzani, 1999) or methods that apply inductive learning techniques to learn the behavior and properties of the candidate classifiers (Chan and Stolfo, 1993; Wolpert, 1992) Constructing ensembles of classifiers is not cheap and produces a final outcome that is expensive due to the increased complexity of the ....

[Article contains additional citation context not shown here]

Merz, C. and Pazzani, M. (1999), `A principal components approach to combining regression estimates', Machine Learning 36, 9--32.

....27, 33, 35, 51, 54] e.g. majority or weighted voting, bagging, etc. techniques that employ referee functions to arbitrate among the predictions generated by the classi ers [7, 20, 22, 50, 21, 23, 34] e.g. arbiters, mixture of experts, etc. methods that rely on principal components analysis [29, 31], e.g. SCANN, or methods that apply inductive learning techniques to learn the behavior and properties of the candidate classi ers [55, 7] e.g. stacking. Our distributed system is designed to support any of these meta learning methods. However, in this study we report results obtained using ....

C. Merz and M. Pazzani. A principal components approach to combining regression estimates. Machine Learning, 36:9-32, 1999.

.... including techniques that combine the set of models in some linear fashion [1, 2, 3, 12, 20, 27, 29, 37, 39, 21] techniques that employ referee functions to arbitrate among the predictions generated by the classifiers, 16, 17, 18, 19, 28, 36] methods that rely on principal components analysis [23, 24] or methods that apply inductive learning techniques to learn the behavior and properties of the candidate classifiers [6, 40] Constructing ensembles of classifiers is not cheap and produces a final outcome that is expensive due to the increased complexity of the final meta classifier. In ....

C. Merz and M. Pazzani. A principal components approach to combining regression estimates. Machine Learning, 1999. In press.

....Kargupta,Weiyun Huang,Krishnamoorthy Sivakumar,Erik Johnson used for detecting linear associative rules [17] Application of PCA based techniques for large scale text can be found in [6] PCA has also found applications in ensemble learning and aggregation of multiple models. Merz and Pazzani [42] have reported a PCA based technique for combining regression estimates. A maximum likelihood based framework for constructing mixture models of PCA is proposed by Tipping and Bishop [49] This e ort is related to the research presented in the current paper. The technique developed by Tippin and ....

C. Merz and M. Pazzani. A principal components approach to combining regression estimates. Machine Learning, 36:9-32, 1999.

.... apply arbitrary learning algorithms to discover the correlations among the available models and compute non linear relations among the classifiers (at the expense, perhaps, of generating less intuitive representations) Other methods for combining multiple models, include Merz and Pazzani s PCR # [41] and Merz s SCANN [40] algorithms. The first integrates ensembles of regression models for improving regression estimates while the latter for improving classification performance. Both rely on methods similar to principal components analysis to map the estimates of the models into a new ....

C. Merz and M. Pazzani. A principal components approach to combining regression estimates. Machine Learning, 1998. In press.

....to discover the correlations among the available models. Meta learning has the advantage of employing an arbitrary learning algorithm for computing non linear relations among the classifiers (at the expense, perhaps, of generating less intuitive representations) Merz and Pazzani s PCR # [22] and Merz s SCANN [21] algorithms are also algorithms that combine multiple models, the first for improving regression estimates, the latter for improving classification performance. The PCR # algorithm maps the estimates of the models into a new representation using principal components analysis ....

C. Merz and M. Pazzani. A principal components approach to combining regression estimates. Machine Learning, 1998. to appear.

....of models have been studied, including techniques that combine the set of models in some linear fashion (egs. 10, 2, 1] techniques that employ referee functions to arbitrate among the predictions generated by the classifiers, 13, 14, 19] methods that rely on principal components analysis [16, 17] or methods that apply inductive learning techniques to learn the behavior and properties of the candidate classifiers [26, 5] Constructing ensembles of classifiers is not cheap and produces a final outcome that is expensive due to the increased complexity of the final meta classifier. In ....

C. Merz and M. Pazzani. A principal components approach to combining regression estimates. Machine Learning, 1998. to appear.

....the classifiers (at the expense, perhaps, of generating less intuitive representations) Our empirical studies in [8] show that meta learning compares favorably against several voting algorithms on partitioned data sets. Other methods for combining multiple models, include Merz and Pazzani s PCR # [35] and Merz s SCANN [34] algorithms. The first integrates ensembles of regression models for improving regression estimates while the latter for improving classification performance. Both rely on methods similar to principal components analysis to map the estimates of the models into a new ....

C. Merz and M. Pazzani. A principal components approach to combining regression estimates. Machine Learning, 1998. to appear.

No context found.

Christoper J. Merz and Michael J. Pazzani. A principal components approach to combining regression estimates. Machine Learning, 36(1-2):9{ 32, 1999.

No context found.

C. Merz and M. Pazzani. A principal components approach to combining regression estimates. Machine Learning, 36:9-32, 1999.

No context found.

Christopher J. Merz. A Principal Components Approach to Combining Regression Estimates. Machine Learning 36, pp 9-32, 1997.

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