DEEP LEARNING AND SIGNAL PROCESSING

This monograph provides a comprehensive synthesis of recent research that demonstrates how deep learning methods can be effectively applied to achieve technological innovation in signal processing.

Deep Learning and Signal Processing takes the reader through the evolution of machine and deep learning, beginning with the foundations of neural networks to advanced architectures such as deep recursive cascaded convolutional neural networks (CNNs), and core deep learning principles, to cutting-edge applications. Practical case studies in multiple areas such as blind equalization, remote sensing image classification, motion deblurring, handwriting recognition, ADHD diagnosis, and more, are integrated with learning points throughout the book.

By bridging theory with real-world applications, the book equips engineering technicians, postgraduate students, researchers, and AI professionals with the expertise to overcome technological bottlenecks in applying deep learning to signal processing within their respective domains.

Contents:

• Getting Started with Deep Learning
• Artificial Neural Networks
• Convolutional Neural Networks
• Deep Generative Adversarial Networks
• Deep Restricted Boltzmann Machine
• Deep Belief Networks
• Deep Sparse Autoencoder
• Recurrent Neural Networks
• Deep Recursive Cascaded Convolutional Neural Networks
• Long Short-Term Memory Networks

Readership: For engineering technicians, researchers and graduate students in the field of information and communication engineering, control science and engineering, or intelligent science and technology; For enterprises and companies working on or that utilize artificial intelligence.