This brief presents an efficient and scalable online learning algorithm for recurrent neural networks (RNNs). The approach is based on the real-time recurrent learning (RTRL) algor...
A recurrent question in the design of intelligent agents is how to assign degrees of beliefs, or subjective probabilities, to various events in a relational environment. In the sta...
In this work, a framework for the reconstruction of smooth surface shapes from shading images is presented. The method is based on using a backpropagationbased neural network for ...
Abstract—In two recent contributions [1], [2], we have provided a comparative analysis of various optimization algorithms, which can be used for atomic location estimation, and s...
Stefano Tennina, Marco Di Renzo, Fabio Graziosi, F...
Abstract— Neural processing of large-scale data sets containing both many input / output variables and a large number of training examples often leads to very large networks. Onc...