Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
Several application and technology trends indicate that it might be both pro table and feasible to move computation closer to the data that it processes. In this paper, we evaluat...
This paper presents an approach to endow a humanoid robot with the capability of learning new objects and recognizing them in an unstructured environment. New objects are learnt, w...
Dario Figueira, Manuel Lopes, Rodrigo M. M. Ventur...
Distributed learning is a problem of fundamental interest in machine learning and cognitive science. In this paper, we present asynchronous distributed learning algorithms for two...
Because changes to the database (DB) and workload occur during a DB system's lifetime, the physical DB design must evolve to sustain good performance. These changes are carri...