Advances in Neural Network/Deep Learning and Symmetry/Asymmetry

Dear Colleagues,

We are presently experiencing a profound utilization of Artificial Intelligence techniques across human society. At the core of this epochal shift stands the Deep Learning methodology, serving as a pivotal enabling technology. Deep neural networks thrive on the abundance of extensive datasets and accessible computing resources. Deep Learning grapples with vast volumes of data, extracting pertinent information and latent knowledge embedded within. Its pervasive influence extends across virtually all facets of contemporary society, notably revolutionizing voice and image recognition, healthcare, and, more recently, natural language processing.

The development of human language is inherent and evolves continuously over a lifetime. However, machines lack this innate ability to evolve without the aid of advanced Deep Learning algorithms. Efforts to refine machine language comprehension have transitioned from statistical to neural language models. Recently, the expansion of pre-trained language models, including Transformer models, has notably boosted Deep Learning's prowess in natural language processing (NLP) tasks by leveraging extensive datasets, enhancing model capacity, and refining performance. The emergence of Large Language Models (LLMs) has significantly impacted both the AI community and broader public spheres, offering the potential for transformative advancements in the development and application of AI algorithms.

On the other hand, symmetry/Asymmetry is a fundamental tool in the exploration of a broad range of complex systems. In deep learning symmetry has been explored in both models and data. Models that satisfy the symmetries of the problem are not only correct but also can produce predictions with smaller errors, using a small amount of training points.

However, even in the modern era, many ponder: what lies beyond? What breakthrough awaits us next? Despite the considerable advancements in Deep Learning, numerous obstacles remain. Deep Learning algorithms typically hinge on extensive datasets for training. Furthermore, the energy consumption required to run these algorithms on conventional computers is significant. Training such networks for practical applications presents a formidable challenge, requiring the utilization of cloud computing resources and powerful GPUs. Thus, if future demand involves deploying these algorithms, for example, in mobile devices, autonomous vehicles, and everyday sensors crucial to digital transformation, the field will have to overcome several substantial hurdles and consider symmetry/asymmetry concepts.

This Special Issue aims to provide a platform for researchers to share their latest advances in neural networks, deep learning, generative adversarial networks, symmetry/asymmetry, and their applications in solving real-world problems.

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

• New architectures and algorithms for neural networks and deep learning;
• Advances in fuzzy neural networks, deep learning and ensemble;
• Advances of symmetry/asymmetry in neural networks and deep learning;
• Applications of neural networks and deep learning in computer vision, speech recognition, natural language processing, and robotics;
• Transferring learning techniques in neural networks and deep learning;
• Interpretable and explainable neural networks and deep learning models;
• Neural network optimization and regularization techniques;
• Automation of training of neural networks and deep learning (automated machine learning, including evolutionary algorithms);
• Deep learning for data analysis and prediction;
• Extracting understanding from large-scale and heterogeneous data;
• Collection of datasets and training of deep learning models;
• Generative Adversarial Network and its applications;
• Trustworthy AI.

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 the Special Issue of Symmetry.

Prof. Dr. Roberto Celio Limao de Oliveira
Prof. Dr. José Alfredo F. Costa
Prof. Dr. Rafael Stubs Parpinelli
Prof. Dr. Eduardo F. Simas Filho
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.

• applicable neural networks theory
• augmented intelligence
• computer vision and image processing
• deep learning
• deep learning applications
• ethical deep learning
• explainable deep learning
• generative adversarial network
• generative pre-trained transformer
• hybrid intelligent systems
• large language models
• neural networks
• neuro-fuzzy systems
• symmetry/asymmetry
• prediction analysis
• supervised and unsupervised learning methods
• transfer learning
• trustworthy deep learning