Symmetry and Asymmetry in Machine Learning

A special issue of Symmetry (ISSN 2073-8994). This special issue belongs to the section "Computer".

Deadline for manuscript submissions: 30 June 2024 | Viewed by 6094

Special Issue Editors

Dr. Qinwei Fan
E-Mail Website
Guest Editor
School of Science, Xi 'an Polytechnic University, Xi'an 710048, China
Interests: neural networks; deep learning; machine learning; computer vision; natural language processing; stochastic optimization
School of Mathematical Sciences, Dalian University of Technology, Dalian 116024, China
Interests: machine learning
Special Issues, Collections and Topics in MDPI journals
School of Mathematics and Statistics, Northeast Normal University, Changchun 130024, China
Interests: neural networks; deep learning; machine learning; computer vision; natural language processing; stochastic optimization
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Machine learning mainly designs and analyzes algorithms that allow computers to learn autonomously. It is widely used in various fields, such as image recognition, speech recognition, natural language processing, recommendation systems, classification, prediction, etc. This Special Issue aims to provide a platform for researchers to share their latest advances in neural networks, and deep learning, and the correlation between machine learning and symmetry as well as their applications to solving real-world problems.

Topics of interest for this Special Issue include, but are not limited to, the following:

  • Symmetry and asymmetry in new architectures and algorithms for machine learning;
  • Faster and more robust methods for the learning of deep models;
  • Advances in fuzzy neural networks, spiking neural networks, extreme learning machines and support vector machines;
  • Machine learning applications in computer vision, speech recognition, natural language processing, and robotics;
  • Neural network theory analysis;
  • Transfer learning for deep learning systems;
  • Deep neural network optimization and regularization technology;
  • Deep learning for data analysis and prediction;
  • Adversarial machine learning and its applications;
  • Meta-learning and ensemble learning;
  • Symmetric networks/asymmetric networks.

We invite researchers to submit their original research articles, reviews, and short communications related to the above topics. All submissions will undergo a rigorous peer-review process, and accepted papers will be published in this Special Issue of Symmetry.

Dr. Qinwei Fan
Dr. Jie Yang
Prof. Dr. Dongpo Xu
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. 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

  • machine learning
  • deep learning
  • convolutional neural networks
  • spiking neural network
  • recurrent neural networks
  • graph neural network
  • long short-term memory
  • extreme learning machine
  • generative adversarial networks
  • reinforcement learning
  • clustering analysis
  • computer vision
  • natural language processing
  • time series analysis
  • model-based clustering modeling high-dimensional

Published Papers (4 papers)

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

Research

Jump to: Review

25 pages, 4232 KiB  
Article
Maintaining Symmetry between Convolutional Neural Network Accuracy and Performance on an Edge TPU with a Focus on Transfer Learning Adjustments
Symmetry 2024, 16(1), 91; https://doi.org/10.3390/sym16010091 - 11 Jan 2024
Viewed by 599
Abstract
Transfer learning has proven to be a valuable technique for deploying machine learning models on edge devices and embedded systems. By leveraging pre-trained models and fine-tuning them on specific tasks, practitioners can effectively adapt existing models to the constraints and requirements of their [...] Read more.
Transfer learning has proven to be a valuable technique for deploying machine learning models on edge devices and embedded systems. By leveraging pre-trained models and fine-tuning them on specific tasks, practitioners can effectively adapt existing models to the constraints and requirements of their application. In the process of adapting an existing model, a practitioner may make adjustments to the model architecture, including the input layers, output layers, and intermediate layers. Practitioners must be able to understand whether the modifications to the model will be symmetrical or asymmetrical with respect to the performance. In this study, we examine the effects of these adjustments on the runtime and energy performance of an edge processor performing inferences. Based on our observations, we make recommendations for how to adjust convolutional neural networks during transfer learning to maintain symmetry between the accuracy of the model and its runtime performance. We observe that the edge TPU is generally more efficient than a CPU at performing inferences on convolutional neural networks, and continues to outperform a CPU as the depth and width of the convolutional network increases. We explore multiple strategies for adjusting the input and output layers of an existing model and demonstrate important performance cliffs for practitioners to consider when modifying a convolutional neural network model. Full article
(This article belongs to the Special Issue Symmetry and Asymmetry in Machine Learning)
Show Figures

Figure 1

18 pages, 8268 KiB  
Article
Self-Supervised Spatiotemporal Masking Strategy-Based Models for Traffic Flow Forecasting
Symmetry 2023, 15(11), 2002; https://doi.org/10.3390/sym15112002 - 31 Oct 2023
Cited by 2 | Viewed by 736
Abstract
Traffic flow forecasting is an important function of intelligent transportation systems. With the rise of deep learning, building traffic flow prediction models based on deep neural networks has become a current research hotspot. Most of the current traffic flow prediction methods are designed [...] Read more.
Traffic flow forecasting is an important function of intelligent transportation systems. With the rise of deep learning, building traffic flow prediction models based on deep neural networks has become a current research hotspot. Most of the current traffic flow prediction methods are designed from the perspective of model architectures, using only the traffic features of future moments as supervision signals to guide the models to learn the spatiotemporal dependence in traffic flow. However, traffic flow data themselves contain rich spatiotemporal features, and it is feasible to obtain additional self-supervised signals from the data to assist the model to further explore the underlying spatiotemporal dependence. Therefore, we propose a self-supervised traffic flow prediction method based on a spatiotemporal masking strategy. A framework consisting of symmetric backbone models with asymmetric task heads were applied to learn both prediction and spatiotemporal context features. Specifically, a spatiotemporal context mask reconstruction task was designed to force the model to reconstruct the masked features via spatiotemporal context information, so as to assist the model to better understand the spatiotemporal contextual associations in the data. In order to avoid the model simply making inferences based on the local smoothness in the data without truly learning the spatiotemporal dependence, we performed a temporal shift operation on the features to be reconstructed. The experimental results showed that the model based on the spatiotemporal context masking strategy achieved an average prediction performance improvement of 1.56% and a maximum of 7.72% for longer prediction horizons of more than 30 min compared with the backbone models. Full article
(This article belongs to the Special Issue Symmetry and Asymmetry in Machine Learning)
Show Figures

Figure 1

14 pages, 1777 KiB  
Article
Application of GA-WELM Model Based on Stratified Cross-Validation in Intrusion Detection
Symmetry 2023, 15(9), 1719; https://doi.org/10.3390/sym15091719 - 07 Sep 2023
Cited by 1 | Viewed by 619
Abstract
Aiming at the problem of poor detection performance under the environment of imbalanced type distribution, an intrusion detection model of genetic algorithm to optimize weighted extreme learning machine based on stratified cross-validation (SCV-GA-WELM) is proposed. In order to solve the problem of imbalanced [...] Read more.
Aiming at the problem of poor detection performance under the environment of imbalanced type distribution, an intrusion detection model of genetic algorithm to optimize weighted extreme learning machine based on stratified cross-validation (SCV-GA-WELM) is proposed. In order to solve the problem of imbalanced data types in cross-validation subsets, SCV is used to ensure that the data distribution in all subsets is consistent, thus avoiding model over-fitting. The traditional fitness function cannot solve the problem of small sample classification well. By designing a weighted fitness function and giving high weight to small sample data, the performance of the model can be effectively improved in the environment of imbalanced type distribution. The experimental results show that this model is superior to other intrusion detection models in recall and McNemar hypothesis test. In addition, the recall of the model for small sample data is higher, reaching 91.5% and 95.1%, respectively. This shows that it can effectively detect intrusions in an environment with imbalanced type distribution. Therefore, the model has practical application value in the field of intrusion detection, and can be used to improve the performance of intrusion detection systems in the actual environment. This method has a wide application prospect, such as network security, industrial control system, and power system. Full article
(This article belongs to the Special Issue Symmetry and Asymmetry in Machine Learning)
Show Figures

Figure 1

Review

Jump to: Research

22 pages, 1747 KiB  
Review
Deep Learning and Neural Networks: Decision-Making Implications
Symmetry 2023, 15(9), 1723; https://doi.org/10.3390/sym15091723 - 08 Sep 2023
Cited by 2 | Viewed by 3294
Abstract
Deep learning techniques have found applications across diverse fields, enhancing the efficiency and effectiveness of decision-making processes. The integration of these techniques underscores the significance of interdisciplinary research. In particular, decisions often rely on the output’s projected value or probability from neural networks, [...] Read more.
Deep learning techniques have found applications across diverse fields, enhancing the efficiency and effectiveness of decision-making processes. The integration of these techniques underscores the significance of interdisciplinary research. In particular, decisions often rely on the output’s projected value or probability from neural networks, considering different values of the relevant output factor. This interdisciplinary review examines the impact of deep learning on decision-making systems, analyzing 25 relevant papers published between 2017 and 2022. The review highlights improved accuracy but emphasizes the need for addressing issues like interpretability, generalizability, and integration to build reliable decision support systems. Future research directions include transparency, explainability, and real-world validation, underscoring the importance of interdisciplinary collaboration for successful implementation. Full article
(This article belongs to the Special Issue Symmetry and Asymmetry in Machine Learning)
Show Figures

Figure 1

Back to TopTop