Entrenamiento dinámico de redes convolucionales profundas para clasificación de imágenes

In recent years, Deep Learning has positioned itself as one of the most successful paradigms for the solution of pattern recognition problems such as image classification. Particularly, CNNs (Convolutional Neural Networks) are one of the most used models for this task. A typical CNN incorporates hundreds of thousands of parameters that must be adjusted in what is known as the training of the network, through the use of large reference training sets. This training represents a high cost in computational time and resources even with the availability of GPUs to do the processing. In this work, an alternative scheme for management of the training data for CNNs is proposed which consists in the selective-adaptive sampling of the data. Through experiments performed on the CIFAR10 dataset for image classification, it is shown that the proposed scheme succeeds in decreasing the training time without significantly sacrificing the performance of the networks.