R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the 1995. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
First 50 documents Next 50
Automated Classification of Keratoconus: - Case Study In (Correct)
....Zealand, http: www.cs.waikato.ac. nz #ml ) This version of C4.5 implements Revision 8, the last public release of C4.5 [27] We used the complete data set available for model construction and performed 10 fold stratified cross validation of the data for model selection and performance evaluation [11]. We evaluate the accuracy of our classifier as well as sensitivity and specificity of the model. 4.1 C4.5 Classification Results The purpose of our first experiment was to systematically explore the relationship between increasing polynomial order and classification accuracy. Our results show an ....
Ron Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In International Joint Conference on Artificial Intelligence, pages 1137--1145, 1995.
Efficient Leave-One-Out Cross-Validation of Kernel Fisher.. - Cawley, Talbot (2003) (Correct)
....procedures based on the leave oneout estimator as the latter is known to exhibit a comparatively high variance. For large datasets, however, it could be argued that the variances of k fold and leave one out estimators are likely to be similar: Lemma 2 (Variance of k fold cross validation [17]) Assuming the training algorithm for a classifier system is stable with regard to the perturbation of the training data introduced during the cross validation procedure (i.e. the perturbation of the training data does not change the decision rule obtained) the variance of the k fold estimate of ....
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the Fourteenth International Conference 18 on Artificial Intelligence (IJCAI), pages 1137--1143, San Mateo, CA, 1995. Morgan Kaufmann.
New Techniques In Intelligent Information Filtering - Macskassy (2003) (Correct)
....of the four text classifiers mentioned in the previous section. I define one classification task as one of the seven classification problems using one of the nine featurizations as described in the previous section. The accuracy of each run was found using ten fold stratified cross validation [Koh95] 7.2.3 Results As I compare many featurizations and classifications in this section, all results will be shown on scatter plots. As outlined in the evaluation methodology, I start by selecting the best performing classifier using only the text features. Then I add the numerical features and ....
....as when the SVM was run as a 123 numerical classifier. 8.3 Evaluation Methodology I use a straight forward comparison of accuracy between classifiers to gauge their performance. The accuracy of a classifier was found by finding the average accuracy using ten fold stratified cross validation [Koh95] Each data set was represented in one of two ways: The original feature encoding using numbers for use with C4.5, SVM, and Ripper. The bag of tokens encoding generated by the entropy method, for use with the five text classification methods. 8.4 Results Figure 8.1 shows the results ....
Ron Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the 14th International Joint Conference on Artificial Intelligence, pages 1137--1143, San Francisco, CA, 1995. Morgan Kaufmann.
Efficient Leave-One-Out Cross-Validation of Kernel Fisher.. - Cawley, Talbot (2003) (Correct)
....procedures based on the leave oneout estimator as the latter is known to exhibit a comparatively high variance. For large datasets, however, it could be argued that the variances of k fold and leave one out estimators are likely to be similar: Lemma 2 (Variance of k fold cross validation [17]) Assuming the training algorithm for a classifier system is stable with regard to the perturbation of the training data introduced during the cross validation procedure (i.e. the perturbation of the training data does not change the decision rule obtained) the variance of the k fold estimate of ....
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the Fourteenth International Conference 18 on Artificial Intelligence (IJCAI), pages 1137--1143, San Mateo, CA, 1995. Morgan Kaufmann.
The Effects Of Pruning Methods On The Predictive.. - Esposito, Malerba, .. (1999) (Correct)
....test set from those in the training set. Thus, the estimates are ne if viewed as comprising a descriptive comparison of performance, but cannot be statistically extrapolated to a wider population. Since in the literature a di erent experimental procedure has been recommended for model selection [30], namely strati ed k fold cross validation with moderate k values (10 20) we have decided to repeat our experiments in order to verify whether the conclusions (1) 4) still hold with cross validation estimates. In the following we present the new experimental design based on 10 fold ....
Kohavi CR. A study of cross validation and bootstrap for accuracy estimation and model selection. Proceedings of the 14th International Joint Conference on Arti,cial Intelligence, 1995; 1137}1143.
Discriminative Naive Bayesian Classifiers - Kaizhu Huang Department (Correct)
....the variable number ranges from 4 to 60 and the sample number varies from 150 to 6435. The diversity in choosing the datesets will make the evaluations on the algorithms more reliably. For the datesets with a small number of samples such as Iris and Vote, we use a five fold Cross Validation method [9] to test the performance. We compare our model s performance with NB and SVM in two cases, namely the case without information missing and the case with information missing. The parameters for DNB and SVM are used in the experiments are listed in Table 2. 4.1 Without information missing We first ....
R. Kohavi. A study of cross validation and bootstrap for accuracy estimation and model selection. In Proceedings of the 14th IJCAI, pages 338--345. San Francisco, CA:Morgan Kaufmann, 1995.
Discriminative Training of Bayesian Chow-Liu Multinet.. - Huang, King, Lyu (2003) (Correct)
....convergence curve for PB 1 . The solid line is the convergence curve for PB 2 . The x axis represents the iteration. And the y axis represents the Euclidean distance between the current value and previous value for each parameter vector. W to 0. 2 and we use the five fold cross validation (CV5) [11] method to test the performance of these methods. The recognition results are described in Table I. It can be observed that DCLT performs significantly better than CLT and NB in this dataset, which shows that incorporating discriminative information will greatly benefit the classifier s ....
R. Kohavi. A study of cross validation and bootstrap for accuracy estimation and model selection. In Proceedings of the 14th IJCAI, pages 338--345. San Francisco, CA:Morgan Kaufmann, 1995.
Weka-Parallel: Machine Learning in Parallel - Celis, Musicant (Correct)
....are completely handled by Weka Parallel. The practitioner is freed from implementing these tasks, and need only ready the remote machines for incoming work requests. 1 Introduction Cross validation is a primary methodology in measuring the success of ma chine learning algorithms [3, 5]. Techniques such as classification, regression, clustering, and feature selection all make use of cross validation techniques in predicting generalization success. Cross validation is inherently parallelizable, as it requires repeatedly breaking the data into different segments, running an ....
R. Kohavi. A study of cross-validation and bootstrap for accuracy esti- mation and model selection. In C.S. Mellish, editor, Proceedings of the 1Jth International Joint Conference on Artificial Intelligence. Morgan Kaufmann, 1995.
Unknown - (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the 1995.
The Maximum-Margin Approach to Learning Text Classifiers -.. - Joachims (2000) (17 citations) (Correct)
No context found.
Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the International Joint Conference cial Intelligence. Morgan Kaufman.
Probabilistic-Weighted k-Nearest-Neighbour Algorithm: a New.. - Sierra, Lazkano (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In N. Lavrac and S. Wrobel, editors, Proceedings of the International Joint Conference on Arti cial Intelligence, 1995.
Combining Bayesian Networks, k Nearest Neighbours.. - Sierra, Lazkano.. (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In N. Lavrac and S. Wrobel, editors, Proceedings of the International Joint Conference on Artificial Intelligence, 1995.
Sensitivity Analysis of the Result in Binary Decision Trees - Alvarez (2004) (Correct)
No context found.
Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. Proc. Int. Joint Conf. on Artificial Intelligence (1995) 1137-1143
Journal of Machine Learning Research 7 (2006) 2149-2187.. - Conditional (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, pages 1137--1143, 1995.
Explaining the result of a Decision Tree to the End-User - Isabelle Alvar Ez (Correct)
No context found.
R. Kohavi, `A study of cross-validation and bootstrap for accuracy estimation and model selection', in IJCAI, pp. 1137--1145, (1995).
Inferring Rule-Based Strategies in Dynamic Judgment Tasks.. - Rothrock, Kirlik (2003) (Correct)
No context found.
QuebecR. Kohavi, "A study of cross-validation and bootstrap for accuracy estimation and model selection," in Proc. Int. Joint Conf. Artificial Intelligence, Montreal, Canada, 1995.
Learning Generative Models of Scene - Features Robert Sim (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the 1995.
Simultaneous Evolution of Neural Network Topologies and.. - Rocha, Cortez, Neves (2005) (Correct)
No context found.
R. Kohavi. A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), Montreal, Quebec, Canada, August 1995.
Model-Based Cluster Analysis for Web Users Sessions - George Pallis Lefteris (Correct)
No context found.
Kohavi R. Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. In Proc. of the 14th International Joint Conference on A.I., Vol. 2, Canada, 1995.
Towards Efficient Texture Classification and Abnormality Detection - Monadjemi (2004) (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of International Joint Conference on Artificial Intelligence, 1995.
A Heuristic for Learning Decision Trees and Pruning.. - Ranilla, Luaces.. (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In IJCAI, pages 1137--1145, 1995.
A Heuristic for Learning Decision Trees and Pruning.. - Ranilla, Luaces.. (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In IJCAI, pages 1137-1145, 1995.
Characteristic Electrocardiograph Intervals as Indices of.. - Shouldice (2004) (Correct)
No context found.
R. Kohavi, "A study of cross validation and bootstrap for accuracy estimation and model selection," Proc 14th Int Joint Conference on Artificial Intelligence, pp. 1137--1143, 1995.
Model-Based Cluster Analysis for Web Users Sessions - George Pallis Lefteris (Correct)
No context found.
Kohavi R. Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. In Proc. of the 14th International Joint Conference on A.I., Vol. 2, Canada, 1995.
Selection of the Most Useful Subset of Genes for Gene.. - Paul, Iba (2004) (Correct)
No context found.
Kohavi, R., "A study of cross-validation and bootstrap for accuracy estimation and model selection", in Proceedings of the International Joint Conference on Artificial Intelligence, 1995.
A Comparison of the Use of Different Wavelet Coefficients.. - de Chazal, Reilly (2000) (Correct)
No context found.
R. Kohavi, "A study of cross validation and bootstrap for accuracy estimation and model selection", In Proceedings of the 14th International Joint Conference on Artificial Intelligence, 1137-1143, 1995.
Automatic Classification of Heartbeats Using ECG.. - de Chazal, O'Dwyer.. (2004) (6 citations) (Correct)
No context found.
R. Kohavi, "A study of cross validation and bootstrap for accuracy estimation and model selection," in Proc. 14th Int. Joint Conf. Artificial Intelligence, 1995, pp. 1137--1143.
Using Wavelet Coefficients for the Classification of the .. - de Chazal, Celler.. (2000) (Correct)
No context found.
R. Kohavi, "A study of cross validation and bootstrap for accuracy estimation and model selection", In Proceedings of the 14th International Joint Conference on Artificial Intelligence, 1137-1143, 1995.
Identification of Informative Genes for Molecular Classification .. - Paul, Iba (2004) (Correct)
No context found.
Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. Proceedings of the International Joint Conference on Artificial Intelligence, 1995.
Classification Of The Electrocardiogram - Using Selected Wavelet (2000) (Correct)
No context found.
R. Kohavi, "A study of cross validation and bootstrap for accuracy estimation and model selection", In Proceedings of the 14th International Joint Conference on Artificial Intelligence, 1137-1143, 1995.
Classification of Protein Localisation Patterns via.. - Anastasiadis.. (Correct)
No context found.
Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. IInternational Joint Conference on Artificial Intelligence.(1995) 223-228
Artificial Intelligence 143 (2003) 51--77 - Www Elsevier Com (2001) (1 citation) (Correct)
No context found.
R. Kohavi, A study of cross-validation and bootstrap for accuracy estimation and model selection, in: Proceedings IJCAI-95, Montreal, QB, Morgan Kaufmann, San Francisco, CA, 1995, pp. 1137--1143.
Morphological Hat-Transform Scale Spaces and Their Use.. - Jalba, Wilkinson.. (Correct)
No context found.
R. Kohavi, A study of cross-validation and bootstrap for accuracy estimation and model selection, in: International Joint Conference on Artificial Intelligence, San Mateo, CA, 1995, pp. 1137--1145.
Choosing between Two Learning Algorithms Based on Calibrated Tests - Bouckaert (2003) (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, pages 1137--1143. San Mateo, CA: Morgan Kaufmann, 1995.
Probabilistic-Weighted k-Nearest-Neighbour Algorithm: a New.. - Sierra, Lazkano (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In N. Lavrac and S. Wrobel, editors, Proceedings of the International Joint Conference on Arti cial Intelligence, 1995.
Algorithmic Stability and Sanity-Check Bounds for Leave-One-Out .. - Kearns, Ron (1997) (42 citations) (Correct)
No context found.
Ron Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In the International Joint Conference on Artifical Intelligence, 1995.
Fast Approximation of the Bootstrap for Model Selection - Simon, Lendasse, Wertz.. (2003) (Correct)
No context found.
R. Kohavi, "A study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection", Proc. of the 14th Int. Joint Conf. on A.I., Vol. 2, Canada, 1995.
Morphological Hat-Transform Scale Spaces And Their Use.. - Classification Jalba.. (2003) (Correct)
No context found.
R. Kohavi, "A study of cross-validation and bootstrap for accuracy estimation and model selection," in Proc. Int. Joint Conf. Artific. Intell., 1995, pp. 1137--1145.
Bootstrap for Model Selection: linear approximation of.. - Simon, Lendasse.. (Correct)
No context found.
R. Kohavi, "A study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection", Proc. of the 14th Int. Joint Conf. on A.I., Vol. 2, Canada, 1995.
Model Selection with Cross-Validations and Bootstraps - .. - Lendasse, Wertz.. (2003) (Correct)
No context found.
Kohavi, R.: A study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection, Proc. of the 14th Int. Joint Conf. on A.I., Vol. 2, Canada, 1995.
No Unbiased Estimator of the Variance of K-Fold.. - Bengio, Grandvalet (2003) (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, pages 1137--1143, 1995. 19
File Classification in Self-* Storage Systems - Mesnier, Thereska, Ganger.. (2004) (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. Fourteenth international joint conference on artificial intelligence, pages 1137-- 1143, 1995.
The PNC 2 Cluster Algorithm - An integrated learning algorithm.. - Haendel (2003) (Correct)
No context found.
Ron Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proc. International Joint Conference on Artificial Intelligence (IJCAI), pages 1137--1145, 1995.
File Classification in Self-* Storage Systems - Mesnier, Thereska, Ellard.. (2004) (Correct)
No context found.
Ron Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. Fourteenth international joint conference on artificial intelligence (San Mateo, CA, 1995.
No Unbiased Estimator of the Variance of K-Fold.. - Bengio, Grandvalet (2003) (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the Fourteenth International Joint Conference on Articial Intelligence, pages 1137--1143, 1995.
Structural Extension to Logistic Regression: - Discriminative Parameter Learning (Correct)
No context found.
R. Kohavi. A study of cross-validation and bootstrap for accuracy estimation and model selection. In IJCAI, 1995.
Multi-View 3-D Object Description with Uncertain Reasoning and.. - Kim (2001) (Correct)
No context found.
R. Kohavi, "A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection," Proc. International Joint Conference on Artificial Intelligence, pp. 1137-1143, 1995.
Ensemble Feature Selection with the Simple Bayesian.. - Alexey Tsymbal Seppo (Correct)
No context found.
Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: C. Mellish (ed.), Proceedings of IJCAI'95, Morgan Kaufmann (1995).
Finite Mixture Model of Bounded Semi-naive Bayesian Networks .. - Huang, King, Lyu (Correct)
No context found.
R. Kohavi. A study of cross validation and bootstrap for accuracy estimation and model selection. In Proceedings of the 14th IJCAI, pages 338--345. San Francisco, CA:Morgan Kaufmann, 1995.
Local Feature Selection with Dynamic Integration of Classifiers - Puuronen, Tsymbal (2001) (Correct)
No context found.
Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection, Proc. 14 International Joint Conference on Artificial Intelligence (C. Mellish, Ed.), Morgan Kaufmann, 1995.
First 50 documents Next 50
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