Symmetry in Neural Networks and Deep Learning
A special issue of Symmetry (ISSN 2073-8994). This special issue belongs to the section "Computer".
Deadline for manuscript submissions: 30 April 2027 | Viewed by 144
Editors
Interests: artificial neural networks; brain/bio-inspired computational intelligence; computer vision; machine learning; control theory and applications; intelligent communication networks
Special Issue Information
Dear Colleagues,
The Special Issue, titled “Symmetry in Neural Networks and Deep Learning”, explores the fundamental and practical roles of symmetry in modern machine learning. Symmetry provides a unifying principle for understanding how neural networks represent, generalize, and learn from structured data. It appears in many forms, including invariance, equivariance, group-theoretic structure, geometric priors, and conservation laws, and it has become increasingly important in the design of efficient, interpretable, and data-efficient learning systems.
This Special Issue welcomes contributions addressing both theoretical and applied aspects of symmetry in deep learning. Topics of interest include, but are not limited to, symmetry-aware architectures, equivariant neural networks, geometric and graph-based deep learning, symmetry in optimization and representation learning, inductive biases for scientific machine learning, and applications in physics, chemistry, computer vision, robotics, and related domains. We also encourage submissions examining the mathematical foundations of learning, as well as empirical studies demonstrating the optimization of robustness, generalization, and computational efficiency.
Dr. Anguo Zhang
Prof. Dr. Xingshuo Han
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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Symmetry 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 2400 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
- artificial neural networks
- deep learning
- invariant representations
- geometric deep learning
- representation learning
- scientific machine learning
- graph neural networks
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.
