Entropy Based Machine Learning Models
A special issue of Entropy (ISSN 1099-4300).
Deadline for manuscript submissions: 31 March 2025 | Viewed by 106
Special Issue Editors
Interests: neural networks; sustainability; information theory; metric topology; stochastic dynamics; statistical mechanics; machine learning; big data
Special Issues, Collections and Topics in MDPI journals
Interests: artificial neural networks; data science; complex networks; connectivity models; pattern recognition; machine learning
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
The process of learning is the ability to remember, retrieve, organize, or associate a pattern of features to generate a body of knowledge. This natural ability inspired an artificial counterpart, named machine learning (ML), which induces rules from a set of data and performs tasks automatically. Some examples of ML tools are neural networks, genetic algorithms, or Bayesian models, which can store or classify samples of patterns. Such patterns can be data series from geology, economy, sociology, physics, biomedicine, astronomy, or weather, for instance, machine learning can help to predict future behavior or to fulfill a local lack of knowledge.
Machine learning models, besides being inspired by natural processes, use concept from statistical physics, specifically entropy. The second law of thermodynamics states that an isolated system evolves spontaneously to form an equilibrium with maximal entropy. This macroscopical definition of entropy can be microscopically understood as a measure of disorder or uncertainty of a large system and has precise formulation in the scope of information theory. Both machine learning and entropy information have a common background pertaining to how a dynamics system relaxes over time to a stationary state, which optimizes its probability, i.e., increases the possible combinations of microstates.
These properties can be used to model a set of patterns of features or predict new patterns that were not presented during the learning process.
The submissions to this Special Issue are expected to contribute to the approaches of machine learning from the viewpoint of information theory. It aims to be a place where researchers share their work on entropy concepts to solve problems in supervised or clustering learning, and investigators on machine learning use information theory to evaluate the accuracy or to develop a dynamical acceleration of the process.
We seek submissions on the interplay between entropy and ML and include the following topics:
- Mutual information measures for machine learning modeling and prediction.
- Entropy-based methods for preprocessing highly structured data.
- Entropy-based ML for predicting data from engineering, medicine, socio-economy, etc.
- Complexity information of hybrid neural network architectures.
Prof. Dr. David Dominguez
Dr. Mario González-Rodríguez
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.
Keywords
- machine learning
- entropy
- mutual information
- neural networks
- Bayesian models
- statistical mechanics
- stochastic dynamics
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.
Further information on MDPI's Special Issue polices can be found here.
