Independent component analysis, a new concept?
Signal Processing - Special issue on higher order statistics
High-order contrasts for independent component analysis
Neural Computation
Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications
Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications
Overlearning in marginal distribution-based ICA: analysis and solutions
The Journal of Machine Learning Research
ICA with Sparse Connections: Revisited
ICA '09 Proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation
Joint Approximate Diagonalization Utilizing AIC-Based Decision in the Jacobi Method
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
An Adaptive Threshold in Joint Approximate Diagonalization by the Information Criterion
ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part I
Optimal Pairwise Fourth-Order Independent Component Analysis
IEEE Transactions on Signal Processing
Adaptive blind source separation for virtually any sourceprobability density function
IEEE Transactions on Signal Processing
An information theoretic approach to joint approximate diagonalization
ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I
A robust objective function of joint approximate diagonalization
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II
| Hi-index | 0.01 |
Joint approximate diagonalization (JAD) is one of well-known methods for solving blind source separation. JAD diagonalizes many cumulant matrices of given observed signals as accurately as possible, where the optimization for each pair of signals is repeated until the convergence. In each pair optimization, JAD should decide whether the pair is actually optimized by a convergence decision condition, where a fixed threshold has been employed in many cases. Though a sufficiently small threshold is desirable for the accuracy of results, the speed of convergence is quite slow if the threshold is too small. In this paper, we propose a new decision condition with an adaptive threshold for JAD under a probabilistic framework. First, it is assumed that the errors in JAD (non-diagonal elements in cumulant matrices) are given by the exponential distribution. Next, it is shown that the maximum likelihood estimation of the probabilistic model is equivalent to JAD. Then, an adaptive threshold is theoretically derived by utilizing the model selection theory. Numerical experiments verify the efficiency of the proposed method for blind source separation of artificial sources and natural images. It is also shown that the proposed method is especially effective when the number of samples is limited.