Probabilistic Models in Machine and Human Learning
A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Information Theory, Probability and Statistics".
Deadline for manuscript submissions: closed (14 November 2023) | Viewed by 11598
Special Issue Editor
Special Issue Information
Dear Colleagues,
Probabilistic models naturally capture the problem of learning from evidence in the presence of uncertainty. As such, probabilistic models feature prominently in machine learning, models of human learning, and AI broadly. Indeed, even neural networks, classically non-probabilistic models, are defined in terms of approximations to probabilistic inference and are adapted to be probabilistic. The depth and breadth of influence of probabilistic models are hard to overstate.
Current applications of probabilistic modeling are evolving rapidly. In human learning, models are developed for ever more nuanced applications from communication, to emotion, to intuitive physics. In machine learning, the successes of deep learning have strongly influenced research by encouraging work on deep Gaussian processes and modifications of neural networks to capture uncertainty. Meanwhile, more classic probabilistic accounts of causality, structure, and nonparametrics continue apace, and connections develop with reinforcement learning. Impressive recent directions span the two fields by considering how to integrate more structured knowledge into less structured approaches, and vice versa.
The goal of this Special Issue is to provide a forum demonstrating the breadth of probabilistic approaches for machine and human learning, and advances at their intersection. In particular, we aim to provide an outlet for rigorous treatments of both fields, in contrast to existing venues which speak from one disciplinary perspective or the other.
Prof. Dr. Patrick Shafto
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
- human learning
- machine learning
- Gaussian process
- learning and development
- approximate inference
- probabilistic programs
- causal reasoning
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.