Feature extraction is one of the most important machine learning issues. Finding suitable attributes of datasets can enormously reduce the dimensionality of the input space, and from a computational point of view can help all of the following steps of pattern recognition problems, such as classification or information retrieval. However, the feature extraction step is usually performed manually. Moreover, depending on the type of data, we can face a wide range of methods to extract features. In this sense, the process to select appropriate techniques normally takes a long time. This work describes the use of recent advances in deep learning approach in order to find a good feature representation automatically. The implementation of a special neural network called sparse autoencoder and its application to two classification problems of the TJ-II fusion database is shown in detail. Results have shown that it is possible to get robust classifiers with a high successful rate, in spite of the fact that the feature space is reduced to less than 0.02% from the original one.