Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 10,000 papers for “Cross-validation”

Cross-validation

Sylvain Arlot · arXiv (Cornell University) · 2017

This text is a survey on cross-validation. We define all classical\ncross-validation procedures, and we study their properties for two different\ngoals: estimating the risk of a given estimator, and selecting the best\nestimator among a given family. For the risk estimation problem, we compute the\nbias (which can also be corrected) and the variance of cross-validation\nmethods. For estimator selection, we first provide a first-order analysis\n(based on expectations). Then, we explain how to take into account second-order\nterms (from variance computations, and by taking into account the usefulness of\noverpenalization). This allows, in the end, to provide some guidelines for\nchoosing the best cross-validation method for a given learning problem.\n

Cited by 0Open access

Cross validation.

Thomas W. Kelsey (254095), Eleanor Ginbey (2833034), Moti M. Chowdhury (2833031) et al. · Figshare · 2016

MSE denotes mean square error. Training error and test error for the 5-folds of the data set. The first and third cross validation sets show slight overfit (error is higher for data not used to fit the model); the second and fourth sets show slight underfit. The overall error of 5.5% is similar to the error found at the cross validation stages.

Cited by 0Open access

Cross Validation.

Faye Orcales (12488403), Lucy Moctezuma Tan (20485841), Meris Johnson-Hagler (20485844) et al. · Figshare · 2024

(A) k-fold cross validation (here shown is 4-fold). (B) Stratified blocked cross validation. Code is provided for both options: regular random k-fold and for stratified blocked cross validation based on MLST. For both options, the initial training and testing data split is stratified based on labels (R, S).

Cited by 0Open access

Cross Validation

Ludwig · Figshare · 2023

Figures that explain the concept of cross-validation

Cited by 0Open access

Cross validation.

Antigoni Elefsinioti (369715), Marit Ackermann (149020), Andreas Beyer (58396) · Figshare · 2015

Three-fold cross validation was applied for each of the three databases independently. Training of the prediction was done based on two-thirds of the reference data. The x-axis represents the predicted from the training parameters while the y-coordinate represents the actual enrichment with true positives in the test set. The data were binned in five bins and the dots show the respective for each bin. The color indicates the source database. For all three datasets predicted and observed results are very close to the ideal case (solid line). The correlation coefficients between predicted and true are reported in the figure legend.

Cited by 0Open access