Guest Editors
Dr. Ivan Izonin, Lviv Polytechnic National University, 79013 Lviv, Ukraine;
University of Birmingham, Birmingham B15 2FG, UK
Prof. Stephane Chretien, Université Lumiere Lyon 2, France
Summary
Artificial Neural Networks (ANNs) have emerged as powerful computational models inspired by the biological neural networks in the human brain. Initially conceived as a simplified abstraction of how neurons work, ANNs have evolved into sophisticated algorithms capable of learning complex patterns and making decisions across diverse domains.
Artificial Neural Networks have revolutionized numerous fields by harnessing the power of computational learning and pattern recognition. From enhancing medical diagnostics to driving innovation in finance and manufacturing, ANNs continue to push the boundaries of what is possible in artificial intelligence. As research and development in this field progress, the impact of ANNs on society is poised to grow, shaping a future where intelligent systems assist and augment human capabilities across diverse domains.
While ANNs have demonstrated remarkable success in various applications, several challenges remain. These include the need for large-scale labeled datasets, issues related to model interpretability, and concerns about bias and fairness in AI systems. Future research aims to address these challenges through advancements in deep learning architectures, such as attention mechanisms and self-supervised learning, as well as ethical frameworks to guide responsible AI deployment.
This Special Issue (SI) focuses on the latest advancements in models, methods, and architectures of Artificial Neural Networks (ANNs), highlighting their transformative applications across diverse fields including computer vision, natural language processing, healthcare, finance, manufacturing and industry 4.0, and beyond.
Keywords
Small Data Approaches based on ANN
Non-iterative training algorithms
Deep Learning Architectures
ANN-based Ensembles
Novel Activation Functions for Neural Networks
Reinforcement Learning in Real-world Scenarios
Transfer Learning Techniques in Neural Networks
Explainable Artificial Intelligence (XAI) in Neural Networks
Federated Learning
Graph Neural Networks
Self-supervised Learning Approaches in Neural Networks
Quantum Neural Networks
Capsule Networks
Hybrid Neural Network Models
Neuro-fuzzy systems
Login
Register
Submit a Paper
Propose a Special lssue