Entropy-Guided Evolutionary Intelligence: Information Dynamics for Adaptive and Explainable Machine Learning
A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Multidisciplinary Applications".
Deadline for manuscript submissions: 30 November 2026 | Viewed by 208
Special Issue Editors
Interests: evolutionary algorithms; image processing; artificial intelligence; swarm optimization; machine learning
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Artificial intelligence systems increasingly operate in uncertain, dynamic, and high-dimensional environments where robustness, adaptability, and interpretability are critical. While gradient-based machine learning has achieved remarkable success, its reliance on differentiability, large-scale supervision, and static optimization frameworks limits its flexibility in complex and evolving contexts.
Evolutionary Artificial Intelligence (EvoAI) offers a biologically inspired alternative grounded in population-based adaptation and emergent search dynamics. However, classical evolutionary approaches often lack principled mechanisms for controlling uncertainty, regulating diversity, and ensuring interpretability.
Information theory—particularly entropy and related measures such as mutual information and relative entropy—provides a rigorous mathematical framework to quantify uncertainty, diversity, and information flow within adaptive systems. When embedded within evolutionary processes, entropy becomes more than a descriptive statistic; it acts as a regulatory principle governing exploration–exploitation balance, diversity preservation, convergence dynamics, and decision transparency.
This Special Issue will explore entropy-guided evolutionary intelligence, an emerging paradigm at the intersection of evolutionary computation, information dynamics, and explainable AI. By integrating information-theoretic measures into evolutionary operators, selection mechanisms, and model evaluation, we aim to develop adaptive learning systems that are
- Robust under uncertainty;
- Self-organizing in complex search spaces;
- Computationally efficient;
- Interpretable and explainable in their decision-making processes.
Contributions are invited on theoretical, methodological, and applied advances, including the following:
- Entropy-based fitness and objective functions in evolutionary learning;
- Information-regulated mutation, recombination, and selection mechanisms;
- Information dynamics and convergence analysis in EvoAI systems;
- Entropy-driven neuroevolution and hybrid deep-evolutionary frameworks;
- Entropy for uncertainty quantification and explainability;
- Adaptive evolutionary learning for autonomous perception and decision systems;
- Applications in complex nonlinear and high-dimensional domains.
With this Special Issue, we seek to advance the theoretical foundations and practical deployment of entropy-guided evolutionary AI, contributing to the development of next-generation intelligent systems capable of autonomous, adaptive, and transparent decision-making.
Dr. Diego Oliva
Prof. Dr. Marco Perez-Cisneros
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 250 words) can be sent to the Editorial Office for assessment.
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 (ML)
- evolutionary algorithms (EAs)
- entropy
- uncertainty
- information theory
- optimization
- entropy-driven evolutionary machine learning
- information-theoretic measures
- evolutionary operators
- complex real-world problems
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.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
