Recent Advances in Artificial Neural Networks: Case Studies and Applications (Intelligent Systems Reference Library, 283)

This book compiles research on the practical implementation of deep learning models and hybrid intelligent systems to tackle diverse and impactful challenges. Artificial Neural Networks (ANNs) and deep learning have profoundly transformed how real-world problems are addressed, enabling intelligent and adaptive solutions across various domains, including agriculture, healthcare, surveillance, natural language processing, multimodal learning, and environmental monitoring. Each chapter presents a specific use case, employing advanced techniques such as LSTM networks, hybrid CNN–BiLSTM architectures, siamese networks, attention mechanisms, YOLO-based object detection models, transformer architectures, and fuzzy inference systems. The collection is distinguished by its methodological rigor and the breadth of its application areas. To ensure a coherent and structured reading experience, this book is organized into three thematic sections: (1) Forecasting and Predictive Modeling, (2) Computer Vision and Multimodal Recognition, and (3) Innovations in Deep Learning Architectures and Applications. This book is a valuable resource for researchers, professionals, graduate students, and practitioners interested in the current landscape and future directions of deep learning. Readers from disciplines such as computer science, engineering, data science, health informatics, and applied artificial intelligence find inspiration and practical guidance for advancing their work in this book.

This book compiles research on the practical implementation of deep learning models and hybrid intelligent systems to tackle diverse and impactful challenges. Artificial Neural Networks (ANNs) and deep learning have profoundly transformed how real-world problems are addressed, enabling intelligent and adaptive solutions across various domains, including agriculture, healthcare, surveillance, natural language processing, multimodal learning, and environmental monitoring. Each chapter presents a specific use case, employing advanced techniques such as LSTM networks, hybrid CNN–BiLSTM architectures, siamese networks, attention mechanisms, YOLO-based object detection models, transformer architectures, and fuzzy inference systems. The collection is distinguished by its methodological rigor and the breadth of its application areas. To ensure a coherent and structured reading experience, this book is organized into three thematic sections: (1) Forecasting and Predictive Modeling, (2) Computer Vision and Multimodal Recognition, and (3) Innovations in Deep Learning Architectures and Applications. This book is a valuable resource for researchers, professionals, graduate students, and practitioners interested in the current landscape and future directions of deep learning. Readers from disciplines such as computer science, engineering, data science, health informatics, and applied artificial intelligence find inspiration and practical guidance for advancing their work in this book.