The article examines how the replacement of the original data with transformed data affects the quality of training of deep neural network models. The author conducts four experiments to assess the impact of data substitution in tasks with small datasets. The first experiment consists in training the model without making changes to the original data set, the second is to replace all images in the original set with transformed ones, the third is to reduce the number of original images and expand the original data set using transformations applied to images, and also in the fourth experiment, the data set is expanded in order to balance the number of images There are more in each class.

Keywords: dataset, extension, neural network models, classification, image transformation, data replacement

The article analyzes the impact of transformation types on the learning quality of neural network classification models, and also suggests a new approach to expanding image sets using reinforcement learning.

Keywords: neural network model, training dataset, data set expansion, image transformation, recognition accuracy, reinforcement learning, image vector