Guest Editors
Dr. Jesús Ángel Román Gallego
Email: zjarg@usal.es
Affiliation: Department of Computer Science and Automatics, Universidad de Salamanca, Zamora, Spain
Homepage:
Research Interests: machine learning, deep learning, swarm intelligence
Dr. María Luisa Pérez Delgado
Email: mlperez@usal.es
Affiliation: Department of Computer Science and Automatics, Universidad de Salamanca, Zamora, Spain
Homepage:
Research Interests: machine learning, deep learning, swarm intelligence
Summary
1. Background and Importance: The advancement of intelligent systems increasingly relies on both sophisticated learning models (Machine Learning and Deep Learning) and bio-inspired collective intelligence approaches like Swarm Intelligence. Innovations in model architectures, optimization algorithms, and their synergistic integration are crucial for developing solutions that are not only accurate but also computationally efficient, scalable, and deployable in real-world, data-intensive domains.
2. Aim and Scope: This Special Issue focuses on the core advancements in the design, improvement, and application of intelligent computational models. It seeks high-quality research on novel architectures, training paradigms, and optimization techniques for Machine Learning and Deep Learning, as well as on the development and application of Swarm Intelligence algorithms. A key interest lies in works that explore the convergence of these fields—for instance, using Swarm Intelligence to enhance the training, architecture search, or deployment efficiency of learning models. Submissions should demonstrate a strong emphasis on computational efficiency, scalability, or innovative applications in areas such as automated detection, cybersecurity, and complex system optimization.
3. Suggested Themes:
· Novel Architectures for Efficient Learning: Design of lightweight, adaptive, modular, or sparsely-activated neural network and ML model architectures.
· Advanced Optimization Algorithms: Innovations in training procedures, loss functions, regularization, and hyperparameter optimization for ML/DL models.
· Swarm Intelligence Algorithms & Analysis: Design, theoretical analysis (e.g., complexity, convergence), and performance improvement of swarm-based and collective intelligence optimization algorithms.
· Synergistic Integration: Use of Swarm Intelligence for neural architecture search (NAS), hyperparameter tuning, feature selection, or ensemble learning to improve ML/DL models.
· Efficient Models for Real-World Applications: Development and deployment of optimized models for computer vision tasks (detection, recognition), cybersecurity (intrusion detection, threat analysis), sensor data processing, and industrial automation.
· Scalability and Distributed Intelligence: Frameworks for scalable training of models, federated learning scenarios, and distributed swarm optimization for large-scale problems.
· Benchmarking and Performance Analysis: Methodologies for evaluating the trade-offs between model accuracy, computational cost, robustness, and energy efficiency in intelligent systems.
Keywords
machine learning, deep learning, swarm intelligence, model architecture, algorithmic optimization, computational efficiency, neural architecture search, intelligent applications
Login
Register
Submit a Paper
Propose a Special lssue