Recent Advances of Computational and Mathematical Applications in Deep Learning

A special issue of Axioms (ISSN 2075-1680). This special issue belongs to the section "Mathematical Analysis".

Deadline for manuscript submissions: 30 July 2024 | Viewed by 1541

Special Issue Editors


E-Mail Website
Guest Editor
Faculty of Technical Sciences, University of Novi Sad, Trg Dositeja Obradovića 6, 21000 Novi Sad, Serbia
Interests: artificial intelligence; machine learning; deep learning; speech recognition; human–computer interaction

E-Mail Website
Guest Editor
Mathematical Institute of the Serbian Academy of Sciences and Arts, Kneza Mihaila 36, 11001 Belgrade, Serbia
Interests: fractional calculus; machine learning; pattern recognition; image processing

E-Mail Website
Guest Editor
Faculty of Information Technology, Alfa BK University, Palmira Toljatija 3, 11070 Novi Beograd, Serbia
Interests: computer vision; shape descriptors; image processing; E-learning

Special Issue Information

Dear Colleagues,

The Special Issue is aimed toward recent theoretical advances and practical computational and mathematical applications in deep learning. The editors would like to provide an opportunity to present state-of-the-art research on the development of cutting-edge neural network model architectures, the understanding, explainability, and interpretability of deep learning models, their mathematical bias and fairness, robustness,  and ethical and societal regulations and considerations, including but not limited to subjects such as image recognition, retrieval, generation and processing, speech, speaker and emotion recognition and synthesis, style translation, generative adversarial models, reinforcement learning, transfer learning, natural language processing, attention mechanisms, transformer-based networks, sequence modelling, data augmentation, time series analysis, biomedical and agricultural applications, computer vision, etc. The Special Issue will address the following non-exhaustive list of topics (however, we also encourage other ideas in the scope of this issue): 

deep learning theory and applications; computational and mathematical applications (information theory; optimization algorithms; probability and statistics; functional analysis; signal processing; graph theory; medical; pharmaceutical; agricultural; automotive; educational; and financial applications; genomic sequence analysis; gaming; etc.); convolutional neural networks; recurrent neural networks; long short-term memory networks; reinforcement learning; transfer learning; autoencoders; attention mechanisms; generative models; transformers; natural language processing; speech and audio processing; object recognition; style transform; scene understanding; classification and clustering; unsupervised; semi-supervised; supervised; and self-supervised learning; explainable AI. 

We hope that the initiative will be attractive to deep learning researchers and experts in mathematical and computational deep learning applications, and we highly encourage you to submit your current research for peer review before the deadline.

Dr. Branislav Popovic
Dr. Marko Janev
Dr. Lazar Kopanja
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. Axioms 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

  • deep learning
  • neural networks
  • generative models
  • autoencoders
  • reinforcement learning
  • transfer learning
  • style translation
  • object recognition
  • signal processing
  • optimization

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

21 pages, 731 KiB  
Article
Computing Transiting Exoplanet Parameters with 1D Convolutional Neural Networks
by Santiago Iglesias Álvarez, Enrique Díez Alonso, María Luisa Sánchez Rodríguez, Javier Rodríguez Rodríguez, Saúl Pérez Fernández and Francisco Javier de Cos Juez
Axioms 2024, 13(2), 83; https://doi.org/10.3390/axioms13020083 - 26 Jan 2024
Viewed by 1050
Abstract
The transit method allows the detection and characterization of planetary systems by analyzing stellar light curves. Convolutional neural networks appear to offer a viable solution for automating these analyses. In this research, two 1D convolutional neural network models, which work with simulated light [...] Read more.
The transit method allows the detection and characterization of planetary systems by analyzing stellar light curves. Convolutional neural networks appear to offer a viable solution for automating these analyses. In this research, two 1D convolutional neural network models, which work with simulated light curves in which transit-like signals were injected, are presented. One model operates on complete light curves and estimates the orbital period, and the other one operates on phase-folded light curves and estimates the semimajor axis of the orbit and the square of the planet-to-star radius ratio. Both models were tested on real data from TESS light curves with confirmed planets to ensure that they are able to work with real data. The results obtained show that 1D CNNs are able to characterize transiting exoplanets from their host star’s detrended light curve and, furthermore, reducing both the required time and computational costs compared with the current detection and characterization algorithms. Full article
Show Figures

Figure 1

Back to TopTop