On blind deconvolution by neural systems

[sfr@unipg.it]

Dear Colleagues,
I take the liberty to announce the availability of the following two new
papers on blind deconvolution by neural systems:

[1] "Analysis of Modified `Bussgang' Algorithms (MBA) for Channel 
    Equalization" (by S. Fiori). To appear in the IEEE Trans. on Circuits 
    and Systems - Part I

Abstract: In our previous works, we introduced two modified `Bussgang' 
algorithms for blind channel equalization based on neural Bayesian iterative 
estimation of the source sequence. They were developed in order to reduce 
the computational complexity of the original `Bussgang' algorithm as well 
as to make it more flexible by introducing a kind of source adaptivity. 
However, the previous work relied on some heuristic findings, validated 
by series of computer-based experiments. The aim of this paper is to 
present a theoretical investigation of some particular aspects of the 
adapting equations, namely, the steady-state conditions, in order to 
ameliorate the performances of the modified `Bussgang' algorithms and to 
better explain their numerical behavior.

[2] "A Fast Fixed-Point Neural Blind Deconvolution Algorithm" (by S. Fiori).
    To appear in the IEEE Trans. on Neural Networks

Abstract: The aim of this contribution is to introduce a new blind 
deconvolution algorithm based on fixed-point optimization of a 
`Bussgang'-type cost function. The cost function relies on approximate 
Bayesian estimation achieved by an adaptive neuron. The main feature 
of the presented algorithm is fast convergence that guarantees good 
deconvolution performances with limited computational demand compared 
to algorithms of the same class.

** The draft versions of these contributions may be downloaded from the
web-page http://www.unipg.it/sfr/ ("Publications" link)

With best regards,
Simone Fiori

Faculty of Engineering - University of Perugia (Italy)
Temporary visitor of Lab. for Mathematical Neuroscience (RIKEN, Japan)