Name
Abstract | ||
|---|---|---|
In this paper a new neural network model for blind demixing of nonlinear mixtures is proposed. We address the use of the adaptive spline neural network recently introduced for supervised and unsupervised neural networks. These networks are built using neurons with flexible B-spline activation functions and in order to separate signals from mixtures, a gradient-ascending algorithm which maximizes the outputs entropy is derived. In particular a suitable architecture composed by two layers of flexible nonlinear functions for the separation of nonlinear mixtures is proposed. Some experimental results that demonstrate the effectiveness of the proposed neural architecture are presented. |
Year | DOI | Venue |
|---|---|---|
2001 | 10.1109/ICASSP.2001.940223 | ICASSP |
Keywords | Field | DocType |
proposed neural architecture,adaptive spline neural network,suitable architecture,nonlinear mixture,nonlinear blind source separation,unsupervised neural network,blind demixing,flexible nonlinear function,new neural network model,flexible b-spline activation function,learning artificial intelligence,blind source separation,computer architecture,adaptive systems,neural networks,neural network,activation function,neural nets,neural network model,spline,unsupervised learning,vectors | Spline (mathematics),Mathematical optimization,Pattern recognition,Computer science,Stochastic neural network,Time delay neural network,Unsupervised learning,Types of artificial neural networks,Artificial intelligence,Artificial neural network,Blind signal separation,Source separation | Conference |
ISBN | Citations | PageRank |
0-7803-7041-4 | 7 | 0.69 |
References | Authors | |
9 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| M. Solazzi | 1 | 7 | 1.03 |
| F. Piazza | 2 | 7 | 0.69 |
| A. Uncini | 3 | 8 | 1.12 |