论文信息 - Nonlinear independent component analysis using ensemble learning: Theory

Nonlinear independent component analysis using ensemble learning: Theory

A nonlinear version of independent component analysis is presented. The mapping from sources to observations is modelled by a multi-layer perceptron network and the distributions of sources are modelled by mixtures of Gaussians. The posterior probability of all the unknown parameters is estimated by ensemble learning. In this paper, we present the theory of the method, and in a companion paper experimental results.

Harri Valpola

[1] Aapo Hyvärinen,et al. Nonlinear independent component analysis: Existence and uniqueness results , 1999, Neural Networks.

[2] Hagai Attias,et al. Independent Factor Analysis , 1999, Neural Computation.

[3] Antti Honkela,et al. Bayesian Non-Linear Independent Component Analysis by Multi-Layer Perceptrons , 2000 .

[4] Juha Karhunen,et al. Nonlinear Independent Component Analysis Using Ensemble Learning: Experiments and Discussion , 2000 .