8 The training of some types of neural networks leads to separable non-linear least squares problems. These problems may be9 ill-conditioned and require special techniques. A robus...
We present an application of multi-objective evolutionary optimization of feed-forward neural networks (NN) to two real world problems, car and face classification. The possibly co...
Feed-forward neural networks (Multi-Layered Perceptrons) are used widely in real-world regression or classification tasks. A reliable and practical measure of prediction "conf...
Georgios Papadopoulos, Peter J. Edwards, Alan F. M...
Studies in the area of Pattern Recognition have indicated that in most cases a classifier performs differently from one pattern class to another. This observation gave birth to th...
Rafael Valle dos Santos, Marley B. R. Vellasco, Ra...
Recently, several algorithms have been proposed for using neural networks in dynamic analysis of small structural systems, and also constructing adaptive material modeling subrout...
In this paper, we present a new decompositional approach for the extraction of propositional rules from feed-forward neural networks of binary threshold units. After decomposing t...
We consider detection of high-energy photons in PET using thick scintillation crystals. Parallax effect and multiple Compton interactions in this type of crystals significantly re...
Alexander M. Bronstein, Michael M. Bronstein, Mich...
Recently, several learning algorithms relying on models with deep architectures have been proposed. Though they have demonstrated impressive performance, to date, they have only b...
Hugo Larochelle, Dumitru Erhan, Aaron C. Courville...