Neuro-Symbolic Machine Learning with a Focus on Entropy
A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Multidisciplinary Applications".
Deadline for manuscript submissions: 20 September 2024 | Viewed by 253
Special Issue Editors
Interests: machine learning; natural language processing; reasoning; large language models
Interests: fuzzy system aggregation; mobile robotics systems; computational intelligence; robotics; artificial intelligence algorithms; human–computer interaction; soft computing
Special Issue Information
Dear Colleagues,
The field of neuro-symbolic machine learning, with a specific emphasis on entropy, explores the integration of symbolic reasoning and neural networks. This interdisciplinary approach aims to combine the strengths of symbolic AI, which excels in logical reasoning, with the learning capabilities of neural networks. Entropy, a measure of uncertainty, plays a crucial role in refining the synergy between these two paradigms. The existing research focuses on leveraging entropy-based techniques to enhance the interpretability, robustness, and generalization of neuro-symbolic models, paving the way for more effective and explainable artificial intelligence systems.
The intersection of neuro-symbolic computing and machine learning has sparked innovative research in recent years, offering new perspectives on addressing the challenges of combining symbolic reasoning with neural network approaches. This Special Issue aims to explore the role of entropy in advancing neuro-symbolic machine learning and understanding its implications across various domains.
Topics of interest for this Special Issue include:
- The integration of symbolic reasoning and neural networks.
- Entropy-based approaches in neuro-symbolic systems.
- Knowledge representation and reasoning in neuro-symbolic models.
- Entropy-driven learning algorithms and techniques.
- Large language models augmented with information retrieval and reasoning.
- The applications of neuro-symbolic ML in real-world scenarios.
- The explainability and interpretability of neuro-symbolic models.
- Entropy-based measures of informativeness of the text generated by large language models.
Dr. Boris A. Galitsky
Dr. Alexander Rybalov
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
- knowledge representation and reasoning in DNN
- symbolic knowledge extraction
- explainable AI methods integrating connectionist and symbolic AI
- enhancing large language models through structured background knowledge
- neuro-symbolic cognitive agents
- neuro-symbolic integration
- integration of logics and probabilities
- neuro-symbolic methods for structure learning
- transfer learning
- connectionist systems performing traditionally symbolic AI tasks
- symbolic systems for connectionist tasks
