Abstract. Deep Neural Networks (DNN) propose a new and efficient ML architecture based on the layer-wise building of several representation layers. A critical issue for DNNs remain...
Abstract. Mobile devices get to handle much information thanks to the convergence of diverse functionalities. Their environment has great potential of supporting customized service...
This research employs unsupervised pattern recognition to approach the thorny issue of detecting anomalous network behavior. It applies a connectionist model to identify user behav...
Abstract. We develop a probabilistic interpretation of non-linear component extraction in neural networks that activate their hidden units according to a softmaxlike mechanism. On ...
Abstract— Cognitive control - the ability to produce appropriate behavior in complex situations - is a fundamental aspect of intelligence. It is increasingly evident that this co...