Title :
A new online unsupervised learning rule for the BSB model
Author :
Chartier, Sylvain ; Proulx, Robert
Author_Institution :
Lab. d´´etudes en intelligence naturelle et artificiell, Univ. du Quebec a Montreal, Montreal, Que., Canada
Abstract :
In this paper it is demonstrated that a new unsupervised learning rule enable a nonlinear model, like the BSB model and the Hopfield network, to learn online correlated stimuli. This rule stabilizes the weight matrix growth to the projection rule in a local fashion. The model has been tested with computer simulations that show that the model is stable over the variations of its free parameters and that it is noise tolerant in the recall task
Keywords :
eigenvalues and eigenfunctions; neural nets; pattern recognition; real-time systems; unsupervised learning; BSB neural networks; eigenvalues; nonlinear model; pattern recognition; unsupervised learning; weight matrix; Artificial neural networks; Computer simulation; Eigenvalues and eigenfunctions; Hebbian theory; Hypercubes; Neural networks; Psychology; Testing; Unsupervised learning; Vectors;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.939061
