Title :
Learning algorithms for a specific configuration of the quantron
Author :
de Montigny, S. ; Labib, Richard
Author_Institution :
Dept. of Math. & Ind. Eng., Polytech. Montreal, Montreal, QC, Canada
fDate :
July 31 2011-Aug. 5 2011
Abstract :
The quantron is a new artificial neuron model, able to solve nonlinear classification problems, for which an efficient learning algorithm has yet to be developed. Using surrogate potentials, constraints on some parameters and an infinite number of potentials, we obtain analytical expressions involving ceiling functions for the activation function of the quantron. We then show how to retrieve the parameters of a neuron from the images it produced.
Keywords :
biology; learning (artificial intelligence); neural nets; pattern classification; artificial neuron model; ceiling functions; learning algorithms; nonlinear classification problems; quantron activation function; surrogate potentials; Algorithm design and analysis; Delay; Equations; Heuristic algorithms; Mathematical model; Neurons; Shape;
Conference_Titel :
Neural Networks (IJCNN), The 2011 International Joint Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
978-1-4244-9635-8
DOI :
10.1109/IJCNN.2011.6033271
