Deep-FS: A feature selection algorithm for Deep Boltzmann Machines
Deep-FS: A feature selection algorithm for Deep Boltzmann Machines is a scholarly work by Georgina Cosma and Aboozar Taherkhani, published in 2018 in ''Neurocomputing''. The main subjects of the publication include restricted Boltzmann machine, MNIST database, Boltzmann machine, pattern recognition, transfer learning, feature selection, deep belief network, deep learning, artificial intelligence, audio signal processing, generative adversarial network, computer science, process, feature, machine learning, artificial neural network, and algorithm. The paper proposes a novel algorithm, Deep Feature Selection (Deep-FS), which is capable of removing irrelevant features from large datasets in order to reduce the number of inputs which are modelled during the learning process.