Neural networks

Special Issue of the Journal Neural Networks on

Neural Networks and Kernel Methods
for Structured Domains

Guest editors: Barbara Hammer, Craig Saunders, Alessandro Sperduti

Structured data


topics - format - submission - important dates - guest editors

Topics

In recent years several researchers have started to consider the adaptive processing of structured data. This interest is motivated by two main reasons:

  1. several very important computational problems in Bioinformatics, Chemistry, document classification and filtering (just to name a few), require the use of some Machine Learning procedure to be properly treated because their complexity does not allow a formal and precise definition of the problem and thus no algorithmic solution to the problem is known; on the other hand experimental data is available and usable by a Machine Learning approach;
  2. in many of the above problems, the objects of interest are more naturally represented via varying-size structured representations, such as sequences, strings, trees, directed or undirected graphs. Moreover, it is commonly believed that any computational process representing these objects via flat fixed-size vectorial representations, risks to discard structural information relevant for solving the task at hand.
The aim of the special issue is to bring together recent works developed mainly into the fields of Recurrent and Recursive Neural Networks, and Kernel Methods, with the hope to function as a conceptual support for the improvement of current technologies and the growth of new integrated methodologies for learning in structured domains.

We encourage submissions within the following non-exhaustive list of topics or related areas:

top


Format

The special issue will appear in the Journal Neural Networks of the International Neural Networks Society.

Format of the submission: Full length papers should contain original research which has not been published or submitted elsewhere. They should be written in English including an abstract summarizing briefly the essential contents. The submission should be accompanied by a cover letter including the name, address, e-mail, and phone number of the author to whom correspondence should be sent. For the submission of the manuscript, no specific formatting requirements need to be fulfilled.

Format of the final article: The final accepted article should be submitted single-column, double-spaced throughout on 21.5x28cm (8.5x11inch) paper with one-inch margin. The article should include the name and affiliations of all authors, including the full mailing address for the corresponding author, a brief abstract, and 3 to 6 keywords. All citations must be in American Psychological Association (APA) alphabetized style. All tables (double spaced) and figures that appear in the text should be provided on a separate sheet of paper. The figure legends should also appear double-spaced on a separate sheet of paper. See the instruction page of the journal for further information.

Style files: For the preparation of a latex-manuscript, authors might want to use the latex style-file provided by the publisher Elsevier. Information is also available for the preparation of text files.

top


Submission

Papers should be submitted in electronic form (ps or pdf) to the following e-mail address until October 18, 2004
(Please note: due to several requests, the deadline has been extended from October 11th by one week. This new deadline is strict!)

specialNN.structure@math.unipd.it

Hard-paper submissions are accepted only if the authors do not have access to electronic facilities, and should be mailed to the following address:

Prof. Alessandro Sperduti, Dipartimento di Matematica Pura ed Applicata, Via Belzoni 7, 35131 Padova, ITALY

The submissions must go directly to us and not to the journal Neural Networks.

top


Important dates

  • Submission of the manuscript:
  • October 18, 2004 (this is the final submission deadline!)
  • Notification of acceptance:
  • first half of April, 2005
  • Final version:
  • June 6, 2005
  • Publication:
  • End 2005

    top


    Guest editors

    Barbara Hammer
    Research Group LNM, Department of Mathematics/Computer Science, University of Osnabrück, Germany
    e-mail: hammer (at) informatik.uni-osnabrueck.de

    Craig Saunders
    Image, Speech and Intelligent Systems group, School of Electronics and Computer Science, University of Southampton, U.K.
    e-mail: cjs (at) ecs.soton.ac.uk

    Alessandro Sperduti
    Dipartimento di Matematica Pura ed Applicata, Università di Padova, Italy
    e-mail: sperduti (at) math.unipd.it

    top


    topics - format - submission - important dates - guest editors

    B.Hammer