Sopena, J.M., Romero, E. and Alqu'ezar, R. (1999). Neural Networks with Periodic and Monotonic Activation Functions: A Comparative Study in Classification Problems. Proc. 9th Int. Conf. Artificial Neural Networks, 323-328. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Evolution of Cubic Spline Activation Functions for.. - Mayer, Schwaiger (2001) (Correct)
.... et al. 1999) presented a number of experiments (with widely used benchmark problems) showing that multilayer feed forward networks with a sine activation function learn two orders of magnitude faster while generalization capacity increases (compared to ANNs with logistic activation function) [6]. 2 Evolution of ANN Structure and Activation Functions The technical platform for the evolution of GMLPs is the netGEN system searching a problem adapted ANN architecture by means of an Evolutionary Algorithm (EA) and training the evolved networks using the Stuttgart Neural Network Simulator ....
Sopena, J.M., Romero, E., Alquezar, R.: Neural networks with periodic and monotonic activation functions: a comparative study in classi cation problems. In: Proceedings of the 9th International Conference on Arti cial Neural Networks. (1999)
Differentiation of Neuron Types by Evolving Activation.. - Mayer, Schwaiger (2002) (Correct)
.... et al. 1999) presented a number of experiments (with widely used benchmark problems) showing that multilayer feed forward networks with a sine activation function learn two orders of magnitude faster while generalization capacity increases (compared to ANNs with logistic activation function) [15]. Our own work along these lines started out with the evolution of neuron types from a prede ned set of monotonous AFs [10] For each neuron an index is evolved which refers to a speci c activation function. Tests on three di erent benchmark problems showed that there is only small room for ....
Josep M. Sopena, Enrique Romero, and Rene Alquezar. Neural networks with periodic and monotonic activation functions: a comparative study in classi cation problems. In Proceedings of the 9th International Conference on Arti cial Neural Networks, 1999.
Maximizing the Margin with Feed-forward Neural - Networks Enrique Romero Self-citation (Romero Alqu'ezar) (Correct)
No context found.
Sopena, J.M., Romero, E. and Alqu'ezar, R. (1999). Neural Networks with Periodic and Monotonic Activation Functions: A Comparative Study in Classification Problems. Proc. 9th Int. Conf. Artificial Neural Networks, 323-328.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC