Information Dynamics: Entropy-Driven Evolutionary Machine Learning
A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Multidisciplinary Applications".
Deadline for manuscript submissions: 31 December 2025 | Viewed by 77
Special Issue Editor
Interests: metaheuristic algorithms; bioinspired computation; image processing; machine learning; optimization
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Machine learning (ML) has become indispensable across a wide range of scientific and technological domains, providing powerful tools that can address complex real-world problems fraught with inherent uncertainties. However, the prevalence of gradient-based optimization in contemporary ML often leads to significant computational costs, susceptibility to local optima, and a reliance on extensive labeled datasets. Evolutionary algorithms (EAs) present a compelling alternative, drawing inspiration from natural selection and conducting population-based searches. However, traditional EAs frequently struggle with the adaptability and efficiency required for navigating intricate, high-dimensional landscapes.
Information theory, particularly entropy, has revolutionized our understanding of information analysis. Its application has extended into soft computing and machine learning, where it serves as a measure of uncertainty and a guiding principle for exploring and exploiting search spaces. Recognizing the versatility of entropy, this Special Issue delves into the burgeoning field of entropy-driven evolutionary machine learning. By seamlessly integrating information-theoretic measures into the evolutionary process, we aim to leverage entropy's capacity to quantify uncertainty and the content of information, thereby directing the search towards regions of high information gain. This approach fosters population diversity and enhances the adaptability of EAs, enabling the dynamic adjustment of evolutionary operators and selection mechanisms. Ultimately, we seek to develop more robust, efficient, and interpretable machine learning systems capable of tackling increasingly complex problems. This Special Issue will focus on the following key areas:
- Entropy-based fitness functions: Utilizing entropy to quantify the quality of solutions and guide evolutionary searches.
- Entropy-driven evolutionary operators: Designing mutation and crossover operators that evolve based on information from individuals and populations.
- Information-theoretic selection mechanisms: Implementing selection strategies that prioritize individuals with high diversity and potential.
- Applications of entropy-driven evolutionary ML: Exploring the use of these techniques in diverse domains such as image processing, natural language processing, robotics, bioinformatics, and the modeling of complex systems.
- Theoretical foundations of entropy-driven evolutionary ML: Investigating the convergence properties, computational complexity, and information-theoretic limits of these algorithms.
- Hybrid approaches: Combining entropy-driven evolutionary ML with other ML techniques, such as deep learning and reinforcement learning.
- Interpretability and explainability: Employing entropy to understand the decision-making process of evolutionary ML models.
Dr. Diego Oliva
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
- 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.
