Uncertainty in Large Neural Systems: Validation, Explanation and Correction of Multidimensional Intelligence in a Multidimensional World II

Dear Colleagues,

Significant progress in data-driven neural artificial intelligence (AI) over recent years has brought great benefits to end-users ranging from health, banking, and security areas to advanced manufacturing and space. Modern AI systems are built using massive volumes of data, both curated and raw, with all the uncertainties inherent to these data. One of the major fundamental barriers limiting further advances and use of AI systems of this type is the problem of validation, explanation, and correction of AI’s decision making. This is particularly important for safety-critical and infrastructural applications, but it is also crucial in other use-cases, including financial, career, education, and health services. High-dimensional data and high-dimensional representations of reality are typical features of modern data-driven AI. There is a fundamental trade-off between the “curse of dimensionality” and the “blessing of dimensionality” in high-dimensional data spaces: some popular low-dimensional methods do not work in high-dimensional data spaces, whereas the blessing of dimensionality makes some simple methods unexpectedly powerful in high dimensionality.

It is well known in brain science that small groups of neurons play an important role in pattern recognition. Mathematical explanation of this effect can be found in the multidimensional nature of data. The single-cell revolution in neuroscience, phenomena of grandmother cells, and sparse coding discovered in the human brain meet the new mathematical blessing of dimensionality ideas.

This Special Issue focuses on the development of mathematical and algorithmic foundations underpinning the problems of uncertainty, validation, explanation, and correction in artificial and natural intelligence.

Prof. Dr. Alexander Gorban
Prof. Dr. Ivan Tyukin
Guest Editors

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.