Efficient Deep Learning Models and Applications

Dear Colleagues,

Efficient Deep Learning Models are increasingly recognized as a key factor for the future of Artificial Intelligence (AI) applications. In recent years, we have witnessed remarkable breakthroughs across nearly all AI domains, largely driven by powerful Deep Learning (DL) models. However, much of this progress has been achieved through massive datasets and extremely high energy consumption, raising important concerns regarding the sustainability, scalability, and accessibility of modern AI technologies.

Among this context, efficient DL approaches, including Randomized and Semi-randomized Models, Deep Reservoir Computing paradigms, Neuromorphic architectures (hardware), Distillation Knowledge and Hybrid Artificial Intelligence (such as physics informed neural networks), have emerged as powerful frameworks for bridging the gap between high-performance computation and data/energy efficiency. These methodologies are attracting growing interest due to their ability to drastically reduce training complexity, enhance interpretability, leverage physical priors, and operate effectively on edge devices or specialized hardware. Their relevance spans varied applications, ranging from scientific discovery to industrial process modeling, control, and automation.

We invite you to contribute to this Special Issue dedicated to Efficient Deep Learning Models and Applications, which will bring together novel theoretical advancements, innovative methodologies, and cutting-edge applications in this rapidly expanding research area.

This Special Issue will highlight emerging techniques that improve computational efficiency, adaptability, robustness, interpretability, and physical consistency in modern AI systems. Contributions may focus on foundational theory, algorithmic developments, benchmarking studies, or application-driven insights.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

• Reservoir Computing;
• Semi-randomized Neural Networks;
• Semi-randomized Large Language Models;
• Deep Reservoir Computing;
• Spiking Neural Networks;
• Knowledge Distillation;
• Interpretable Machine Learning;
• Neuromorphic Hardware for Deep Learning;
• Electronic and Photonic Neuromorphic Hardware;
• Quantum Computing;
• Quantum Reservoir Computing;
• Kernel Methods;
• Bayesian Methods;
• Graph Machine Learning;
• Dynamical System Modelling;
• Continuous-time Recurrent Neural Networks and Neural ODEs;
• Neural Dynamic Model Decomposition;
• Physics-informed Neural Networks;
• Neural State Space Models;
• Reinforcement Learning;
• Process Control;
• Model Predictive Control;
• Nonlinear Control;
• Signal Processing;
• Time Series;
• Bioinformatics;
• Natural Language Processing;
• Physics Applications;
• Industrial Applications;
• Industrial Process Modeling.

We look forward to receiving your contributions.

Dr. Luca Pedrelli
Dr. Stefano Dettori
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.