Federated Learning (FL) is a distributed machine learning (ML) framework where several clients work together to solve traditional distributed machine learning tasks without disclosing their local private information to third parties. FL functions without requiring cloud storage of user data, which guarantees privacy while enabling smarter models, reduced latency, and less power use. However, numerous algorithmic and computational challenges had to be solved before Federated Learning could be implemented. This book will contain chapters that describe the uses of machine learning and deep learning to classify Federated Learning. It will cover the definition, architecture, classification, and development process of FL and provide an explanation of the concept through a comparison with traditional distributed learning. Furthermore, the book will discuss common FL issues that must be resolved. Several federated machine learning algorithms, with a focus on deep learning and classification, will be briefly explained and compared, building upon the foundation of classical Federated Learning algorithms. Lastly, the book will cover the breadth of FL based on deep learning and potential future advances.