This paper provides a comprehensive survey of the intersection between deep learning and mobile and wireless networking. It bridges the gap between these two fields by discussing the potential of deep learning in addressing the challenges of managing increasing mobile traffic, real-time analytics, and network resource management in 5G systems. The authors introduce essential background on deep learning techniques and their applications to networking, highlighting the advantages of deep learning in handling complex, heterogeneous data and large volumes of information. They also review several platforms and methods that facilitate the deployment of deep learning on mobile systems, including dedicated libraries, optimization algorithms, and parallel computing techniques. The paper categorizes mobile and wireless networking research based on deep learning into different domains and provides guidelines for model selection and adaptation to specific mobile networking tasks. Finally, it identifies current challenges and future research directions, aiming to guide researchers and practitioners in leveraging deep learning for mobile and wireless networking.This paper provides a comprehensive survey of the intersection between deep learning and mobile and wireless networking. It bridges the gap between these two fields by discussing the potential of deep learning in addressing the challenges of managing increasing mobile traffic, real-time analytics, and network resource management in 5G systems. The authors introduce essential background on deep learning techniques and their applications to networking, highlighting the advantages of deep learning in handling complex, heterogeneous data and large volumes of information. They also review several platforms and methods that facilitate the deployment of deep learning on mobile systems, including dedicated libraries, optimization algorithms, and parallel computing techniques. The paper categorizes mobile and wireless networking research based on deep learning into different domains and provides guidelines for model selection and adaptation to specific mobile networking tasks. Finally, it identifies current challenges and future research directions, aiming to guide researchers and practitioners in leveraging deep learning for mobile and wireless networking.