Tech moves fast! Stay ahead of the curve with Techopedia!
Join nearly 200,000 subscribers who receive actionable tech insights from Techopedia.
In machine learning, a validation set is used to “tune the parameters” of a classifier. The validation test evaluates the program’s capability according to the variation of parameters to see how it might function in successive testing.
The validation set is also known as a validation data set, development set or dev set.
Ideally, the program will have three data sets: a training set, a validation set and a test set. In the first step, the training, the program is using training data to learn and build a model. In the second phase, the validation helps to deal with issues like overfitting, where the program may not be calibrated well to handle future data. In terms of the complex equations that result from training and test iterations, engineers talk about “local minima and maxima,” which denote segments of the output process that can help the engineers decide where to “end” a phase. In the third stage, the test stage, new test data is brought in to see if the machine performs as well and accurately on test data as it did on training data, or whether a wide gulf between performance on the two stages indicates overfitting has occurred.