Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.0
2.3
Journals
Mathematics
Special Issues
Deep Neural Networks: Theory, Algorithms and Applications
share announcement

Deep Neural Networks: Theory, Algorithms and Applications

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Computational and Applied Mathematics".

Deadline for manuscript submissions: 31 March 2025 | Viewed by 6518

Special Issue Editors

Prof. Dr. Osslan Osiris Vergara Villegas

E-Mail Website
Guest Editor
Departamento de Ingeniería Industrial y Manufactura, Universidad Autónoma de Ciudad Juaréz, Ciudad Juárez, Mexico
Interests: computer vision; augmented reality; mechatronics
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Vianey Guadalupe Cruz Sánchez

E-Mail Website
Guest Editor
Institute of Engineering and Technology, Universidad Autonoma de Ciudad Juarez, Av. del Charro, 450 norte, Ciudad Juárez, Chihuahua, Mexico
Interests: artificial intelligence; neural networks; computer vision; augmented reality
Prof. Dr. Vicente García

E-Mail Website
Guest Editor
División Multidisciplinaria en Ciudad Universitaria, Universidad Autónoma de Ciudad Juárez, Av. José de Jesús Delgado 18100, Ciudad Juárez 32310, Chihuahua, Mexico
Interests: big data classification; meta-learning; class imbalance; time series; ensembles, neural networks
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Machine Learning (ML) algorithms, as a central branch of Artificial Intelligence (AI), are changing how automatic classification tasks are solved. Moreover, thanks to the progress in hardware technologies, the researchers are experimenting with a significant change oriented to using Deep Learning (DL) techniques instead of traditional ML. Nowadays, DL can be implemented not only in powerful computers but also in mobile devices.

One example of DL is a Deep Neural Network (DNN). A DNN comprises many hidden layers between the input and output layers. Using a DNN, it is less challenging to encounter responses to problems that only offered answers in the past.

This Special Issue aims to help the scientific community disseminate new theories, advances, and applications regarding Deep Neural Networks. We welcome theoretical and practical papers. Topics of interest include, but are not limited to:

  • Novel Deep Neural Networks Architectures.
  • Theoretical Explanations of Deep Neural Networks.
  • Applications of Deep Neural Networks.
  • Transfer Learning in Deep Neural Networks.
  • Managing Extensive and Short Data Sets with Deep Neural Networks.
  • Integration of Hybrid Models.
  • Hardware implementation of Deep Neural Networks.

Prof. Dr. Osslan Osiris Vergara Villegas
Prof. Dr. Vianey Guadalupe Cruz Sánchez
Prof. Dr. Vicente García
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. Mathematics is an international peer-reviewed open access semimonthly 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

  • deep learning
  • convolutional neural networks
  • deep believe networks
  • deep reinforcement learning
  • generative adversarial networks
  • recursive neural networks
  • transformers

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.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

17 pages, 8979 KiB  
Article
Action Recognition in Videos through a Transfer-Learning-Based Technique
by Elizabeth López-Lozada, Humberto Sossa, Elsa Rubio-Espino and Jesús Yaljá Montiel-Pérez
Mathematics 2024, 12(20), 3245; https://doi.org/10.3390/math12203245 - 17 Oct 2024
Viewed by 655
Abstract
In computer vision, human action recognition is a hot topic, popularized by the development of deep learning. Deep learning models typically accept video input without prior processing and train them to achieve recognition. However, conducting preliminary motion analysis can be beneficial in directing [...] Read more.
In computer vision, human action recognition is a hot topic, popularized by the development of deep learning. Deep learning models typically accept video input without prior processing and train them to achieve recognition. However, conducting preliminary motion analysis can be beneficial in directing the model training to prioritize the motion of individuals with less priority for the environment in which the action occurs. This paper puts forth a novel methodology for human action recognition based on motion information that employs transfer-learning techniques. The proposed method comprises four stages: (1) human detection and tracking, (2) motion estimation, (3) feature extraction, and (4) action recognition using a two-stream model. In order to develop this work, a customized dataset was utilized, comprising videos of diverse actions (e.g., walking, running, cycling, drinking, and falling) extracted from multiple public sources and websites, including Pexels and MixKit. This realistic and diverse dataset allowed for a comprehensive evaluation of the proposed method, demonstrating its effectiveness in different scenarios and conditions. Furthermore, the performance of seven pre-trained models for feature extraction was evaluated. The models analyzed were Inception-v3, MobileNet-v2, MobileNet-v3-L, VGG-16, VGG-19, Xception, and ConvNeXt-L. The results demonstrated that the ConvNeXt-L model yielded the most optimal outcomes. Furthermore, using pre-trained models for feature extraction facilitated the training process on a personal computer with a single graphics processing unit, achieving an accuracy of 94.9%. The experimental findings and outcomes suggest that integrating motion information enhances action recognition performance. Full article
(This article belongs to the Special Issue Deep Neural Networks: Theory, Algorithms and Applications)
►▼ Show Figures

Figure 1

19 pages, 15496 KiB  
Article
Building an Analog Circuit Synapse for Deep Learning Neuromorphic Processing
by Alejandro Juarez-Lora, Victor H. Ponce-Ponce, Humberto Sossa-Azuela, Osvaldo Espinosa-Sosa and Elsa Rubio-Espino
Mathematics 2024, 12(14), 2267; https://doi.org/10.3390/math12142267 - 20 Jul 2024
Viewed by 1215
Abstract
In this article, we propose a circuit to imitate the behavior of a Reward-Modulated spike-timing-dependent plasticity synapse. When two neurons in adjacent layers produce spikes, each spike modifies the thickness in the shared synapse. As a result, the synapse’s ability to conduct impulses [...] Read more.
In this article, we propose a circuit to imitate the behavior of a Reward-Modulated spike-timing-dependent plasticity synapse. When two neurons in adjacent layers produce spikes, each spike modifies the thickness in the shared synapse. As a result, the synapse’s ability to conduct impulses is controlled, leading to an unsupervised learning rule. By introducing a reward signal, reinforcement learning is enabled by redirecting the growth and shrinkage of synapses based on signal feedback from the environment. The proposed synapse manages the convolution of the emitted spike signals to promote either the strengthening or weakening of the synapse, represented as the resistance value of a memristor device. As memristors have a conductance range that may differ from the available current input range of typical CMOS neuron designs, the synapse circuit can be adjusted to regulate the spike’s amplitude current to comply with the neuron. The circuit described in this work allows for the implementation of fully interconnected layers of neuron analog circuits. This is achieved by having each synapse reconform the spike signal, thus removing the burden of providing enough power from the neurons to each memristor. The synapse circuit was tested using a CMOS analog neuron described in the literature. Additionally, the article provides insight into how to properly describe the hysteresis behavior of the memristor in Verilog-A code. The testing and learning capabilities of the synapse circuit are demonstrated in simulation using the Skywater-130 nm process. The article’s main goal is to provide the basic building blocks for deep neural networks relying on spiking neurons and memristors as the basic processing elements to handle spike generation, propagation, and synaptic plasticity. Full article
(This article belongs to the Special Issue Deep Neural Networks: Theory, Algorithms and Applications)
►▼ Show Figures

Figure 1

25 pages, 9992 KiB  
Article
Analog Implementation of a Spiking Neuron with Memristive Synapses for Deep Learning Processing
by Royce R. Ramirez-Morales, Victor H. Ponce-Ponce, Herón Molina-Lozano, Humberto Sossa-Azuela, Oscar Islas-García and Elsa Rubio-Espino
Mathematics 2024, 12(13), 2025; https://doi.org/10.3390/math12132025 - 29 Jun 2024
Viewed by 1213
Abstract
Analog neuromorphic prototyping is essential for designing and testing spiking neuron models that use memristive devices as synapses. These prototypes can have various circuit configurations, implying different response behaviors that custom silicon designs lack. The prototype’s behavior results can be optimized for a [...] Read more.
Analog neuromorphic prototyping is essential for designing and testing spiking neuron models that use memristive devices as synapses. These prototypes can have various circuit configurations, implying different response behaviors that custom silicon designs lack. The prototype’s behavior results can be optimized for a specific foundry node, which can be used to produce a customized on-chip parallel deep neural network. Spiking neurons mimic how the biological neurons in the brain communicate through electrical potentials. Doing so enables more powerful and efficient functionality than traditional artificial neural networks that run on von Neumann computers or graphic processing unit-based platforms. Therefore, on-chip parallel deep neural network technology can accelerate deep learning processing, aiming to exploit the brain’s unique features of asynchronous and event-driven processing by leveraging the neuromorphic hardware’s inherent parallelism and analog computation capabilities. This paper presents the design and implementation of a leaky integrate-and-fire (LIF) neuron prototype implemented with commercially available components on a PCB board. The simulations conducted in LTSpice agree well with the electrical test measurements. The results demonstrate that this design can be used to interconnect many boards to build layers of physical spiking neurons, with spike-timing-dependent plasticity as the primary learning algorithm, contributing to the realization of experiments in the early stage of adopting analog neuromorphic computing. Full article
(This article belongs to the Special Issue Deep Neural Networks: Theory, Algorithms and Applications)
►▼ Show Figures

Figure 1

24 pages, 22476 KiB  
Article
Method for Human Ear Localization in Controlled and Uncontrolled Environments
by Eydi Lopez-Hernandez, Andrea Magadan-Salazar, Raúl Pinto-Elías, Nimrod González-Franco and Miguel A. Zuniga-Garcia
Mathematics 2024, 12(7), 1062; https://doi.org/10.3390/math12071062 - 1 Apr 2024
Viewed by 1111
Abstract
One of the fundamental stages in recognizing people by their ears, which most works omit, is locating the area of interest. The sets of images used for experiments generally contain only the ear, which is not appropriate for application in a real environment, [...] Read more.
One of the fundamental stages in recognizing people by their ears, which most works omit, is locating the area of interest. The sets of images used for experiments generally contain only the ear, which is not appropriate for application in a real environment, where the visual field may contain part of or the entire face, a human body, or objects other than the ear. Therefore, determining the exact area where the ear is located is complicated, mainly in uncontrolled environments. This paper proposes a method for ear localization in controlled and uncontrolled environments using MediaPipe, a tool for face localization, and YOLOv5s architecture for detecting the ear. The proposed method first determines whether there are cues that indicate that a face exists in an image, and then, using the MediaPipe facial mesh, the points where an ear potentially exists are obtained. The extracted points are employed to determine the ear length based on the proportions of the human body proposed by Leonardo Da Vinci. Once the dimensions of the ear are obtained, the delimitation of the area of interest is carried out. If the required elements are not found, the model uses the YOLOv5s architecture module, trained to recognize ears in controlled environments. We employed four datasets for testing (i) In-the-wild Ear Database, (ii) IIT Delhi Ear Database, (iii) AMI Ear Database, and (iv) EarVN1.0. Also, we used images from the Internet and some acquired using a Redmi Note 11 cell phone camera. An accuracy of 97% with an error of 3% was obtained with the proposed method, which is a competitive measure considering that tests were conducted in controlled and uncontrolled environments, unlike state-of-the-art methods. Full article
(This article belongs to the Special Issue Deep Neural Networks: Theory, Algorithms and Applications)
►▼ Show Figures

Graphical abstract

26 pages, 5580 KiB  
Article
Demystifying Deep Learning Building Blocks
by Humberto de Jesús Ochoa Domínguez, Vianey Guadalupe Cruz Sánchez and Osslan Osiris Vergara Villegas
Mathematics 2024, 12(2), 296; https://doi.org/10.3390/math12020296 - 17 Jan 2024
Viewed by 1527
Abstract
Building deep learning models proposed by third parties can become a simple task when specialized libraries are used. However, much mystery still surrounds the design of new models or the modification of existing ones. These tasks require in-depth knowledge of the different components [...] Read more.
Building deep learning models proposed by third parties can become a simple task when specialized libraries are used. However, much mystery still surrounds the design of new models or the modification of existing ones. These tasks require in-depth knowledge of the different components or building blocks and their dimensions. This information is limited and broken up in different literature. In this article, we collect and explain the building blocks used to design deep learning models in depth, starting from the artificial neuron to the concepts involved in building deep neural networks. Furthermore, the implementation of each building block is exemplified using the Keras library. Full article
(This article belongs to the Special Issue Deep Neural Networks: Theory, Algorithms and Applications)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop