Daniele Vigliano

An information theoretic approach to a novel nonlinear independent component analysis paradigm

This paper introduces a novel independent component analysis (ICA) approach to the separation of nonlinear convolutive mixtures. The proposed model is an extension of the well-known post nonlinear (PNL) mixing model and consists of the convolutive mixing of PNL mixtures. Theoretical proof of existence and uniqueness of the solution under proper assumptions is provided. Feedforward and recurrent demixing architectures based on spline neurons are introduced and compared. Source separation is performed by minimizing the mutual information of the output signals with respect to the network parameters. More specifically, the proposed architectures perform on-line nonlinear compensation and score function estimation by proper use of flexible spline nonlinearities, yielding a significant performance improvement in terms of source pdf matching and algorithm speed of convergence. Experimental tests on different signals are described to demonstrate the effectiveness of the proposed approach.

Generalized splitting functions for blind separation of complex signals

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 Louivilles 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.

Video Compression by Neural Networks

In this chapter a general overview of most common approaches to video compression is first provided. Standardization issues are briefly discussed and most recent neural compression techniques reviewed. In addition, a particularly effective novel neural paradigm is introduced and described. The new approach is based on a proper quad-tree segmentation of video frames and is capable to yield a considerable improvement with respect to existing standards in high quality video compression. Experimental tests are described to demonstrate the efficacy of the proposed solution.

A novel recurrent network for independent component analysis of post nonlinear convolutive mixtures

The paper introduces a novel independent component analysis approach to the separation of nonlinear convolutive mixtures. In particular, convolutive mixing of post nonlinear mixtures is considered. Source separation is performed by a new efficient recurrent network, which is able to ensure faster training with respect to currently available feedforward architectures, with lower computational costs. The proposed architecture makes proper use of flexible spline neurons for on-line estimation of the score function. Experimental results are described to demonstrate the effectiveness of the proposed technique.

Generalized Flexible Splitting Function Outperforms Classical Approaches in Blind Signal Separation of Complex Environment

This paper introduces a novel approach of blind separation in complex environment based on bi-dimensional flexible activation function (AF) and compares the performance of this architecture with the classical approach. The generalized complex function has been realized by a flexible bi-dimensional spline based approach both for the real and one for the imaginary parts, avoiding the restriction due to the Louivilles theorem. The flexibility of the surface allows the learning of the control points using a gradient-based techniques. Some experimental results demonstrate the effectiveness of the proposed method.

A Flexible ICA Approach to a Novel BSS Convolutive Nonlinear Problem: Preliminary Results

This paper introduces a Flexible ICA approach to a novel blind sources separation problem. The proposed on line algorithm performs the separation after the convolutive mixing of post nonlinear convolutive mixtures. The Flexibility of the algorithm is given by the on line estimation of the score function performed by Spline Neurons. Experimental results are described to show the effectiveness of the proposed technique.

A Flexible Natural Gradient Approach to Blind Separation of Complex Signals

In this paper a natural gradient approach to blind source separation in complex environment is presented. It is shown that signals can be successfully reconstructed by a network based on the so called generalized splitting activation function (GSAF). This activation function, whose shape is modified during the learning process, is based on a couple of bi-dimensional spline functions, one for the real and one for the imaginary part of the input, thus avoiding the restriction due to the Louivilles theorem. In addition recent learning metrics are compared with the classical ones in order to improve the speed convergence. Several experimental results are shown to demonstrate the effectiveness of the proposed method.

An IIR architecture for BSS in strong nonlinear convolutive environments

This paper introduces an IIR flexible ICA approach to the problem of blind source separation in convolutive nonlinear environments. The proposed algorithm performs separation in the presence of convolutive mixing of post nonlinear convolutive mixtures (CPNL-C), it is based on redundancy reduction and realizes source separation by minimizing the output mutual information. Experimental results are described to show the effectiveness of the described technique

A recurrent ICA approach to a novel BSS convolutive nonlinear problem

This paper introduces a Recurrent Flexible ICA approach to a novel blind sources separation problem in convolutive nonlinear environment. The proposed algorithm performs the separation after the convolutive mixing of post nonlinear convolutive mixtures. The recurrent neural network produces the separation by minimizing the output mutual information. Experimental results are described to show the effectiveness of the proposed technique.

Nonlinear ICA solutions for convolutive mixing of PNL mixtures

This paper introduces an ICA approach to a nonlinear convolutive BSS problem. The mixing model considered here is an evolution of the post nonlinear one: it is the convolutive mixing of PNL mixture. The main aim of this paper is to enlarge the set of blind sources separation problems that can be approached by nonlinear ICA with some stricter mixing environments than the one just widely described in literature. The flexibility of the algorithm is given by the on line estimation of the score function performed by spline neurons.