In this paper, a kernel-based SOM-face method is proposed to recognize expression variant faces under the situation of only one training image per person. Based on the localization...
In this paper, two modified constrained learning algorithms are proposed to obtain better generalization performance and faster convergence rate. The additional cost terms of the ...
This paper presents a wavelet neural-network for learning and approximation of chaotic time series. Wavelet-networks are inspired by both feed-forward neural networks and the theo...
Abstract—Fingerprinting localization techniques provide reliable location estimates and enable the development of location aware applications especially for indoor environments, ...
Christos Laoudias, Paul Kemppi, Christos G. Panayi...
Deep autoencoder networks have successfully been applied in unsupervised dimension reduction. The autoencoder has a "bottleneck" middle layer of only a few hidden units, ...