Neural Networks and Deep Learning: Advancing Computer Vision and Autonomous Systems

Dear Colleagues,

We are delighted to invite your contributions to this Special Issue, titled “Neural Networks and Deep Learning: Advancing Computer Vision and Autonomous Systems”. The profound progress in deep learning methodologies has instigated a revolutionary shift, moving visual intelligence from passive analysis to active, real-time perception and control. This Special Issue aims to explore and consolidate research that defines the next generation of visual and autonomous capabilities.

This collection focuses on the synergistic advancement of deep learning (DL) algorithms and their robust implementation within intelligent, autonomous platforms. The integration of highly efficient and novel neural network architectures is critical for enabling systems to operate safely and effectively in dynamic, resource-constrained environments. We welcome original contributions across the entire research pipeline—from theoretical algorithmic breakthroughs to high-impact practical applications—with the purpose of serving as a definitive resource that bridges the gap between foundational DL research and its practical deployment.

We seek submissions that address the ongoing challenges of computational efficiency, model interpretability, and architectural complexity required for autonomous operations. We aim to define new best practices for robust real-time performance and system-level autonomy by examining how perception seamlessly integrates into the control loop.

Key areas of interest for submissions include, but are not limited to, the following:

• Advanced Visual Architectures: Developing and evaluating emerging deep learning structures, such as diffusion models, graph convolutional networks, and new Transformer variants, for enhancing traditional computer vision tasks like segmentation, recognition, and classification.
• Dimensionality and Spatial Reasoning: Innovative techniques for analyzing and utilizing complex spatial information, including three-dimensional image and video analysis, motion prediction, and geometric scene reconstruction methods, such as Neural Radiance Fields (NeRFs).
• Deep Learning for Autonomy and Action: Applications focusing on how visual and sensor data are processed by deep learning models to inform control systems, path planning, and multi-agent coordination within autonomous systems.
• Efficiency and Embedded AI: Methods for optimizing deep models (e.g., quantization, pruning, and hardware-aware design) to facilitate high-speed, real-time visual processing capability on embedded and resource-constrained devices.
• Foundational Learning Paradigms: Exploring data-efficient training methods, including self-supervised, generative, and contrastive learning, and analysis of alternative training algorithms.

We hope to make this a significant resource for the research community and look forward to hearing from you.

Dr. Mohammed Abdulhakim Al-Absi
Dr. Ahmed Abdulhakim Al-Absi
Dr. Baseem Al-Athwari
Dr. Nadhem Ebrahim
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-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics 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 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.

• deep learning
• computer vision
• autonomous systems
• neural network architectures
• vision-language models (VLMs)
• multimodal learning
• visual-text fusion
• multimodal transformers
• image-text representation learning
• cross-modal retrieval
• 3D reconstruction
• real-time processing
• sensor fusion
• generative models
• self-supervised learning
• unmanned aerial vehicles (UAVs)
• graph neural networks (GNNs)
• model compression
• motion analysis
• robotics