Deep Network Learning and Its Applications

Dear Colleagues,

Deep learning is becoming the leading approach in machine learning. Supervised, unsupervised, reinforcement, and hybrid, as well as single-view and multi-view learning approaches in deep learning, have been successfully applied in a variety of contexts, spanning from computer vision to natural language processing and data analytics. Deep learning techniques often require huge volumes of data, from which hidden knowledge can be extracted. Today, these data are generated by companies, public organizations, people (e.g., via smartphones), and machines (i.e., the Internet of Things) at a high pace. However, practical deployment is challenging, in a key part due to the high computational needs. Another drawback relies on the implementation of these deep learning applications in high-risk sectors where human oversights must be guaranteed, as recently highlighted by the EU Council. This issue is related to the challenge of putting humans at the center of the development and offering comprehensibility for end-users. The implementation and deployment in practice of deep learning applications is an active area of research from which a series of insights and clues can be captured so as to better shape the future of deep learning applications in our lives.

This Special Issue seeks papers dealing not only with the design of deep learning applications, but also (and with a special interest) the implementation, validation, testing, and/or management of such deep learning systems in simulated/operational environments. Moreover, we look for contributions providing practical guidelines in the development and management of these applications. Papers tackling issues related to the deployment of deep learning systems with final stakeholders/users are welcome. In addition, of particular interest in this Special Issue are deep learning applications conceived for beneficial and benign outcomes, i.e., to support people’s daily life, protect their interests, and enhance their well-being.

Thus, the primary contributions we expect concern not only algorithmic novelties, but also evidence from and the aspects involved when putting deep learning into practice.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

• Law and techno-regulation;
• Critical data studies;
• Computer sound and music;
• Economics and finance;
• Bioinformatics;
• Learning analytics;
• Internet of Things;
• Information retrieval;
• Knowledge extraction/discovery;
• Decision support;
• Human–machine cooperation/interaction;
• Visual interfaces;
• Human-centered AI (comprehensible AI).

Dr. Guarino Alfonso
Dr. Rocco Zaccagnino
Dr. Emiliano Del Gobbo
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. Big Data and Cognitive Computing 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 1800 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.

• deep learning
• deep learning applications
• deep learning in practice
• user study
• deep learning implementation