Abstract. In the last years, several papers have proposed to adopt multiobjective evolutionary algorithms (MOEAs) to generate Mamdani fuzzy rulebased systems with different trade-o...
Michela Antonelli, Pietro Ducange, Beatrice Lazzer...
In recent years, many efforts have been put in applying the concept of reconfigurable computing to neural networks. In our previous pursuits, an innovative self-organizing learning...
Abstract. An abstract recurrent neural network trained by an unsupervised method is applied to the kinematic control of a robot arm. The network is a novel extension of the Neural ...
We present a novel learning framework for pipeline models aimed at improving the communication between consecutive stages in a pipeline. Our method exploits the confidence scores ...
In sequential decision-making problems formulated as Markov decision processes, state-value function approximation using domain features is a critical technique for scaling up the...