Efficient training algorithms for a class of shunting inhibitory convolutional neural networks

This article presents some efficient training algorithms, based on first-order, second-order, and conjugate gradient optimization methods, for a class of convolutional neural networks (CoNNs), known as shunting inhibitory convolution neural networks. Furthermore, a new hybrid method is proposed, whi...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2005-05, Vol.16 (3), p.541-556
Hauptverfasser:	Fok Hing Chi Tivive, Bouzerdoum, A.
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Applied sciences Artificial intelligence Artificial neural networks Biological neural networks Computer science control theory systems Computer Simulation Connectionism. Neural networks Convergence Convolution Convolutional neural network (CoNN) Error analysis Exact sciences and technology first- and second-order training methods Least squares methods Models, Statistical Neural Inhibition Neural networks Neural Networks (Computer) Neurons Numerical Analysis, Computer-Assisted Optimization methods Pattern recognition Pattern Recognition, Automated - methods Regression Analysis shunting inhibitory neuron Signal Processing, Computer-Assisted Stochastic Processes Studies
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!