Dear Colleagues,

For almost ten years, artificial intelligence has been in full swing and has accumulated new successive breakthroughs at both theoretical and practical levels. Deep neural networks such as convolutional neural networks (CNN), long short-term memory (LSTM), and Google's BERT have multiplied the success of deep learning approaches, enabling new ways of arranging decision trees (e.g., extreme gradient boosting) and leading to the progression of "white box" models. Many new paradigms have also been introduced, such as echo state networks or wavelet scattering regressions, making it easier to analyze the theory and quality measures of such automatic learning tools.

However, much work remains to be done at the theoretical level, for example, to have a better understanding of the success of deep learning approaches or to ensure that new paradigms reflect the state of the art in terms of prediction quality. Similarly, very recent approaches to automatic learning are currently being poorly applied to real data, whereas such applications would provide a better understanding of these new paradigms, seeking to know, for example, why, in a given dataset, the computing reservoir produces excellent results while in other situations predictions are disappointing.

The objective of this Special Issue is to bring together new theoretical advances and their applications to real data, in order to confront theory with reality and to raise new avenues for automatic learning, whether supervised or not.

Prof. Christophe Guyeux
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• Artificial intelligence
• Deep learning
• Theory and practice