Title :
An ensemble learning approach to independent component analysis
Author :
Choudrey, R. ; Penny, W.D. ; Roberts, S.J.
Author_Institution :
Dept. of Eng. Sci., Oxford Univ., UK
Abstract :
Independent Component Analysis (ICA) is an important tool for extracting structure from data. ICA is traditionally performed under a maximum likelihood scheme in a latent variable model and in the absence of noise. Although extensively utilised maximum likelihood estimation has well known drawbacks such as overfitting and sensitivity to local-maxima. We propose a Bayesian learning scheme, Variational Bayes or Ensemble Learning, for both latent variables and parameters in the model
Keywords :
array signal processing; data analysis; feature extraction; learning (artificial intelligence); maximum likelihood estimation; neural nets; Bayesian learning scheme; Ensemble Learning; Variational Bayes; blind source separation; ensemble learning approach; feature extraction; independent component analysis; latent variable model; maximum likelihood scheme; neural nets; signal processing; structure from data; Bayesian methods; Blind source separation; Data mining; Feature extraction; Gaussian noise; Independent component analysis; Maximum likelihood estimation; Sensor phenomena and characterization; Signal processing; Source separation;
Conference_Titel :
Neural Networks for Signal Processing X, 2000. Proceedings of the 2000 IEEE Signal Processing Society Workshop
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-6278-0
DOI :
10.1109/NNSP.2000.889436
