The phrase "as data augmentation" is correct and usable in written English.
It can be used in contexts related to machine learning, data processing, or research where additional data is generated to improve model performance.
Example: "We applied various techniques as data augmentation to enhance the training dataset and improve the model's accuracy."
Alternatives: "in the form of data augmentation" or "as a method of data augmentation".
The EM algorithm implicitly enlarges the data size by using latent variables for the mixture probability, referred to as data augmentation [45].
This is a major advantage over other Bayesianly proper methods such as data augmentation (Tanner and Wong 1987) that assume a common distribution for all of the variables.
The computational differences listed in the above paragraph are theoretical however, since often other estimations (such as data augmentation) need to be performed alongside eigenvalue decompositions, which do not require calculation of new eigenvalues.
Here Mendel's law of segregation was utilized to assign the two parental alleles with equal probabilities, and then applying the method of data augmentation, as a part of the resulting Bayesian computation.
One solution would be to use data augmentation techniques as in Didelot et al. (2010).
To accommodate varying rates across sites (or among-site rate variation), we use a similar data augmentation approach as before, which now additionally imputes evolutionary rates in order to avoid summing the likelihood over all the possible rate classes.
We used the data augmentation algorithm (as described under the heading "Joint modelling imputation") to perform joint modelling imputation under the general location model and the joint prior given in the general location example (see example 4 of the Results), setting hyperparameters τ = ν = 1/2 and κ = 3/2.
Differences in risk estimates of a given factor and across breast cancer subtypes were analyzed using the data augmentation method as described by Lunn and McNeil, using a likelihood ratio test to compare the model with and without interaction terms between the exposure of interest and breast cancer subtype [ 23].
Differences between BMI, waist and hip circumferences and risk of breast cancer subtypes were analyzed using the data augmentation method as described by Lunn and McNeil, using a log likelihood ratio test to compare the model with and without interaction terms between the anthropometric variable and breast cancer subtype [ 27].
To cope with the subjective variance of the user input, as well as to expand the size of the training set, data augmentation was performed for the training data.
We set the patch size as 45 × 45 and use data augmentation (rotation or flip) to prepare training data.
