Dear Colleagues,

Discovery of interesting knowledge from complex databases is one of the most important applied problems and theoretical challenges in data science and technology. Many approaches to the notions of “interestingness” and “complexity” have been proposed during the last three decades. Nevertheless, we have to return to these topics again and again, because no satisfactory general theory which meets all of the challenges exists. We need to evaluate the complexity of high dimensional and large datasets and reveal what interesting knowledge exists inside.

Many of the approaches to interestingness and complexity are based on entropy and related notions. The modern development of the theory of measure concentration effects in high dimensions bring new light and new challenges: Essentially multidimensional datasets are boring from most of points of view and the discovery of reliable and interesting knowledge from them becomes a very difficult task.

Dimensionality reduction is a fundamental part of complexity analysis and facilitates the extraction of interesting and new information. Two limit cases have been studied in some depth: (i) reducible complexity which allows for the extraction of non-trivial, low-dimensional structures, and (ii) the self-averaging complexity which becomes simple analysis of multidimensional spheres and normal distributions. The no-man’s land between these extremes may well be very important in the development of complex artificial intelligence (AI) and in the study of real and artificial neural nets.

We invite papers on entropic methods in the analysis of the complexity of high-dimensional data and the extraction interesting knowledge from them. Related topics from the theory and methods of AI, neural networks and mathematical neurosciences are also welcome. We also encourage contributions that aim at exploring the connections of the measure concentration theory with complexity of high dimension data, knowledge interestingness, curse and blessing of dimensionality.

Prof. Dr. Alexander N. Gorban
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. Entropy is an international peer-reviewed open access monthly 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.