Online learning and generalization of parts-based image representations by Non-Negative Sparse Autoencoders. Neural Networks. 33:194–203.. 2012.
Regularization and stability in reservoir networks with output feedback. Neurocomputing. 90:96–105.. 2012.
Representation and Generalization of Bi-manual Skills from Kinesthetic Teaching. IEEE-RAS International Conference on Humanoid Robots. :560–567.. 2012.
A constrained regularization approach for input-driven recurrent neural networks. Differential Equations and Dynamical Systems. 19:27–46.. 2011.
Neural learning and dynamical selection of redundant solutions for inverse kinematic control. Proc. IEEE Int. Conf. Humanoid Robots. :564–569.. 2011.
Reservoir regularization stabilizes learning of Echo State Networks with output feedback. Proc. European Symposium on Artificial Neural Networks. :59–64.. 2011.
State prediction: a constructive method to program recurrent neural networks. Artificial Neural Networks and Machine Learning – ICANN 2011 : 21st International Conference on Artificial Neural Networks, Espoo, Finland, June 14-17, 2011, Proceedings, Part I. 6791:159–166.. 2011.
Efficient online learning of a non-negative sparse autoencoder. European Symposium Artificial Neural Networks. :1–6.. 2010.
Recurrence Enhances the Spatial Encoding of Static Inputs in Reservoir Networks. Proc. Int. Conf. Artificial Neural Networks. :148–153.. 2010.
Tacking reduces bow-diving of high-speed unmanned sea surface vehicles. Int. Symp. Learning and Adaptive Behavior in Robotic Systems. :177–182.. 2010.
Attractor-based computation with reservoirs for online learning of inverse kinematics. European Symposium Artificial Neural Networks (ESANN). :257–262.. 2009.
Goal-directed movement generation with a transient-based recurrent neural network controller. Advanced Technologies for Enhanced Quality of Life. :112–117.. 2009.
Reaching movement generation with a recurrent neural network based on learning inverse kinematics for the humanoid robot iCub. IEEE Conf. Humanoid Robotics. :323–330.. 2009.
Recurrent neural associative learning of forward and inverse kinematics for movement generation of the redundant PA-10 robot. Int. Symp. Learning Adaptive Behavior in Robotic Systems, best paper award. 1:35–40.. 2008.