Input feature extraction for multilayered perceptrons using supervised principal component analysis

SJ Perantonis, V Virvilis - Neural processing letters, 1999 - Springer
A method is proposed for constructing salient features from a set of features that are given as
input to a feedforward neural network used for supervised learning. Combinations of the …

A new approach to perceptron training

C Eitzinger, H Plach - IEEE Transactions on Neural Networks, 2003 - ieeexplore.ieee.org
The training of perceptrons is discussed in the framework of nonsmooth optimization. An
investigation of Rosenblatt's perceptron training rule shows that convergence or the failure …

Real-time automatic linear feature detection in images

G Zeng - 2008 - search.proquest.com
Linear feature detection in digital images is an important low-level operation in computer
vision that has many applications. In remote sensing tasks, it can be used to extract roads …

[CITATA][C] Εκπαίδευση μονοστρωματικών δικτύων σε πεπερασμένο αριθμό βημάτων και εποπτευόμενη προεπεξεργασία δεδομένων

Β Βιρβίλης - 1999 - didaktorika.gr
Στον σεβαστό και φίλο επιβλέποντα ερευνητή κ. Σ. Περαντώνη ερευνητή του ΕΚΕΦΕ
'ΔΗΜΟΚΡΙΤΟΣ', ο οποίος παρ'όλες τις πολυποίκιλες υποχρεώσεις του στάθηκε …