Название: Cognitive Machine Intelligence: Applications, Challenges, and Related Technologies
Автор: Inam Ullah Khan, Salma El Hajjami, Mariya Ouaissa, Salwa Belaqziz
Издательство: CRC Press
Серия: Intelligent Data-Driven Systems and Artificial Intelligence
Год: 2025
Страниц: 373
Язык: английский
Формат: pdf (true)
Размер: 12.9 MB

Cognitive Machine Intelligence: Applications, Challenges, and Related Technologies offers a compelling exploration of the transformative landscape shaped by the convergence of Machine Intelligence, Artificial Intelligence (AI), and cognitive computing. In this book, the authors navigate through the intricate realms of technology, unveiling the profound impact of cognitive machine intelligence on diverse fields such as communication, healthcare, cybersecurity, and smart city development. The chapters present study on robots and drones to the integration of Machine Learning with wireless communication networks, IoT, quantum computing, and beyond. The book explores essential role of Machine Learning in healthcare, security, and manufacturing. With a keen focus on privacy, trust, and the improvement of human lifestyles, this book stands as a comprehensive guide to the novel techniques and applications driving the evolution of cognitive machine intelligence. The vision presented here extends to smart cities, where AI-enabled techniques contribute to optimal decision-making, and future computing systems address end-to-end delay issues with a central focus on Quality-of-Service metrics. Cognitive Machine Intelligence is an indispensable resource for researchers, practitioners, and enthusiasts seeking a deep understanding of the dynamic landscape at the intersection of Artificial Intelligence and cognitive computing.

Numerous breakthroughs in the field of Machine Learning, namely in Deep Learning, have been made as a result of increased availability of computing resources and processing capability. Deep Learning facilitates the extraction of pertinent, conceptual, and advanced characteristics from input data, hence enhancing their applicability as classifiers and detectors. This approach is commonly referred to as the representation-­based learning methodology, which draws inspiration from the cognitive processes and functioning of the human mind. The core concept behind generative models, specifically deep learning-­based models, is the primary focus of generative adversarial networks (GANs). The field of image synthesis has garnered significant attention. The aforementioned phrase pertains to the procedure of generating a visual representation by utilizing the concealed and revealed attributes of the image. GANs are frequently employed in the domain of imaging algorithms in a broad sense owing to their shown efficacy in handling image data. GANs consist of a pair of models that undergo simultaneous training through adversarial interactions.

This book:

Covers a comprehensive exploration of cognitive machine intelligence and its intersection with emerging technologies such as federated learning, blockchain, and 6G and beyond.
Discusses the integration of Machine Learning with various technologies such as wireless communication networks, ad-hoc networks, software-defined networks, quantum computing, and big data.
Examines the impact of machine learning on various fields such as healthcare, unmanned aerial vehicles, cyber security, and neural networks.
Provides a detailed discussion on the challenges and solutions to future computer networks like end-to-end delay issues, Quality of Service (QoS) metrics, and security.
Emphasizes the need to ensure privacy and trust while implementing the novel techniques of machine intelligence.

It is primarily written for senior undergraduate, graduate students, and academic researchers in the fields of electrical engineering, electronics and communication engineering, and computer engineering.