Deep learning has fundamentally transformed engineering practice, enabling unprecedented capabilities in pattern recognition, predictive analytics, and automated decision-making across diverse domains. This edited book presents cutting-edge research at the intersection of artificial intelligence and engineering, featuring contributions that span theoretical foundations, methodological innovations, and real-world applications. From explainable AI frameworks that bridge the gap between model accuracy and interpretability in safety-critical systems, to language-specific transformer models for detecting hate speech in Turkish social media, the chapters illustrate how deep learning architectures must be thoughtfully adapted to address domain-specific challenges. The book explores petroleum demand forecasting in Nigeria's transitioning energy sector, demonstrating how machine learning algorithms can optimize supply chains and inform policy decisions, alongside comprehensive investigations of BERT-based keyword extraction for morphologically complex languages such as Arabic and Turkish. By synthesizing advances in convolutional neural networks, recurrent architectures, and transformer models, this book offers both academic insights and practical guidance for researchers, engineers, and practitioners seeking to harness the full potential of deep learning.

This book is included in DOAB.