Self-Learning in Physical Machines
A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Statistical Physics".
Deadline for manuscript submissions: closed (20 April 2024) | Viewed by 173
Special Issue Editor
Interests: soft matter physics; physical learning algorithms; machine learning; metamaterials; smart matter; programmable matter; neuromorphic computing; statistical physics; computational neuroscience; mechanics; learning theory
Special Issue Information
Dear Colleagues,
In recent years, we have made great strides in the general understanding of learning phenomena in physical systems, where learning is understood as an analogy to neurological processes and computational machine learning (ML) algorithms. These research efforts lie in the intersection of physics, neuroscience and computer science and use insights and techniques from these fields to design and characterize self-learning machines that autonomously adapt functional properties and behaviors while observing examples of use.
Physical learning constitutes a fascinating emergent collective phenomenon that can be naturally described by the philosophy and tools of condensed matter and statistical physics. This unifying perspective may afford deeper insight into the universal aspects of learning in the real world under physical constraints. Such insight can help illuminate biological and computational learning, as well as suggest practical ways of realizing smart learning materials.
This Special Issue on self-learning machines will highlight recent exciting developments and ideas in the field, touching upon physical and biological learning studied both theoretically and experimentally. We invite authors to present original research articles or review articles on topics including, but not limited to:
- Self-learning machines in different media (electrical, optical, mechanical, etc.);
- Neuromorphic computing;
- Novel physical computation;
- Biologically plausible learning;
- The physics of learning.
Dr. Menachem Stern
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.
Keywords
- self-learning
- learning machines
- physical learning
- inverse design
- neuromorphic computing
- biologically plausible learning
- smart matter
- functional matter
- novel computation
