Independent component analysis: algorithms and applications
Neural Networks
Independent Component Analysis: Principles and Practice
Independent Component Analysis: Principles and Practice
Artificial Neural Networks with Adaptive Multidimensional Spline Activation Functions
IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 3 - Volume 3
Non linear satellite radio links equalized using blind neural networks
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
Neural Networks: A Comprehensive Foundation (3rd Edition)
Neural Networks: A Comprehensive Foundation (3rd Edition)
Complex backpropagation neural network using elementary transcendental activation functions
ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 200. on IEEE International Conference - Volume 02
IEEE Transactions on Signal Processing
On the complex backpropagation algorithm
IEEE Transactions on Signal Processing
The complex backpropagation algorithm
IEEE Transactions on Signal Processing
Multilayer feedforward networks with adaptive spline activation function
IEEE Transactions on Neural Networks
Blind signal processing by complex domain adaptive spline neural networks
IEEE Transactions on Neural Networks
A Flexible Natural Gradient Approach to Blind Separation of Complex Signals
Proceedings of the 2009 conference on New Directions in Neural Networks: 18th Italian Workshop on Neural Networks: WIRN 2008
A Partitioned Frequency Block Algorithm for Blind Separation in Reverberant Environments
Proceedings of the 2009 conference on Neural Nets WIRN09: Proceedings of the 19th Italian Workshop on Neural Nets, Vietri sul Mare, Salerno, Italy, May 28--30 2009
A Pre-Filtering and Post-Filtering Approach to Blind Source Separation
Proceedings of the 2011 conference on Neural Nets WIRN10: Proceedings of the 20th Italian Workshop on Neural Nets
| Hi-index | 0.01 |
This paper proposes the blind separation of complex signals using a novel neural network architecture based on an adaptive nonlinear bi-dimensional activation function (AF); the separation is obtained maximizing the output joint entropy. Avoiding the restriction due to the Louiville's theorem, the AF is composed of a couple of bi-dimensional spline functions, one for the real and one for the imaginary part of the signal. The surface of this function is flexible and it is adaptively modified according to the learning process performed by a gradient-based technique. The use of the bi-dimensional spline defines a new class of flexible AFs which are bounded and locally analytic. This paper aims to demonstrate that this novel bi-dimensional complex AF outperforms the separation in every environment in which the real and imaginary parts of the complex signal are not decorrelated. This situation is realistic in a large number of cases.