The article presents the results of a numerical experiment comparing the accuracy of neural network recognition of objects in images using various types of data set extensions. It describes the need to expand data sets using adaptive approaches in order to minimize the use of image transformations that may reduce the accuracy of object recognition. The author considers such approaches to data set expansion as random and automatic augmentation, as they are common, as well as the developed method of adaptive data set expansion using a reinforcement learning algorithm. The algorithms of operation of each of the approaches, their advantages and disadvantages of the methods are given. The work and main parameters of the developed method of expanding the dataset using the Deep-Q-Network algorithm are described from the point of view of the algorithm and the main module of the software package. Attention is being paid to one of the machine learning approaches, namely reinforcement learning. The application of a neural network for approximating the Q-function and updating it in the learning process, which is based on the developed method, is described. The experimental results show the advantage of using data set expansion using a reinforcement learning algorithm using the example of the Squeezenet v1.1 classification model. The comparison of recognition accuracy using data set expansion methods was carried out using the same parameters of a neural network classifier with and without the use of pre-trained weights. Thus, the increase in accuracy in comparison with other methods varies from 2.91% to 6.635%.
Keywords: dataset, extension, neural network models, classification, image transformation, data replacement
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