Simulated annealing and Boltzmann machines: a stochastic approach to combinatorial optimization and neural computing
Independent component analysis, a new concept?
Signal Processing - Special issue on higher order statistics
A fast fixed-point algorithm for independent component analysis
Neural Computation
Alternating projections onto convex sets
Deconvolution of images and spectra (2nd ed.)
A neural learning algorithm for blind separation of sources based on geometric properties
Signal Processing - Special issue on neural networks
The Geometry of Algorithms with Orthogonality Constraints
SIAM Journal on Matrix Analysis and Applications
A novel conjugate gradient based block adaptive ICA algorithm for dynamic environments
ICECS'05 Proceedings of the 4th WSEAS international conference on Electronics, control and signal processing
Hi-index | 0.00 |
This paper presents a new procedure for Blind Separtion of non-Gaussian Sources. It is proven that the estimation of the separating system can be based on the cancellation of some second partial derivatives of the output cross-cumulants. The resulting method is based on a conjutate gradient algorithm on the Stiefel manifold. Simulated annealing is used to obtain a good initial value and improve the rate of convergence.