Call for papers
Algorithms and Architectures: statistical learning algorithms based on ICA and BSS using linear mixture models, nonlinear models, convolutive and noisy models, extensions of basic models, combinatorial optimization, kernel methods, graphical models, etc. Applications: innovative applications or fielded systems that use ICA and BSS, including systems for time series prediction, data mining, bioinformatics, text/web analysis, multimedia processing, telecommunications. Brain Imaging: neuroimaging, EEG (electroencephalogram), ERP (event related potentials), MEG (magnetoencephalogram), fMRI (functional magnetic resonance imaging), applications in neuroscience. Emerging Technologies: analog and digital VLSI implementations, photonics. Speech and Signal Processing: source separation, auditory perception, coding, recognition, synthesis, denoising, segmentation, psychoacoustics, dynamical systems, dynamic and temporal models. Theory: information theory, estimation methods, tensorial methods, complex methods, properties of generalization, time/frequency representations, frame theory, model selection, optimization, regularization, spaces of functions and kernels, online method analysis, asymptotic analysis, related unsupervised machine learning, hierarchical models, general theory of statistical dependency, hypergraphical models, relation to problems in coding. Visual and Sensory Processing: image processing and coding, segmentation, object detection and recognition, motion detection and tracking, visual scene analysis and interpretation, models for natural sensory systems: visual including color, auditory, olfactory, receptive fields, motor coding.Demonstrations: Authors wishing to submit to the Demonstration track should consult the Conference web site. Student Paper Contest: Papers submitted with a student as the first author will be eligible to enter the competition. Review Criteria: Submissions will be refereed on the basis of technical quality, novelty, significance, and clarity. There will be an opportunity after the meeting to revise accepted manuscripts. We particularly encourage submissions by authors new to ICA/BSS, as well as application papers that combine concrete results on novel or previously unachievable applications with analysis of the underlying difficulty from a statistical processing perspective. Paper Format: Submissions may be up to eight pages in length, including figures and references, in single-column format, using a font no smaller than 10 points, except for the abstract, a font of 9 points may be used. Please refer to Springer's LNCS webpage for detailed information regarding the submission/publication process. Submissions violating these guidelines will not be considered. Web links to supplementary material (e.g. software, videos) may appear in the paper, but reviewers will not be required to view the supplementary material. Proceedings: Proceedings will be published in Springer-Verlag's Lecture Notes in Computer Science Series (LNCS). LNCS is published, in parallel to the printed books, in full-text electronic form. Instructions about the preparation of a final proceedings version will be sent to the authors of accepted papers. Submission Instructions: ICA 2006 accepts only electronic submissions in postscript and PDF format. The Conference web site will accept electronic submissions until midnight EST, October 15, 2005.