The brain has an inherent advantage over traditional computers in that it possesses the ability to acquire knowledge and skills via the process of learning. Nevertheless, the edge is being swiftly eradicated by a new cohort of artificial intelligence programs known as deep neural networks. The primary objective of this book is to assist readers in comprehending fundamental principles before progressing towards refining their programming abilities, ultimately enabling them to become proficient practitioners in the field of deep learning. The book covers fundamental principles in deep learning, exploring various deep learning designs such as recurrent neural networks. Additionally, it delves into contemporary advancements such as generative adversarial networks. The book serves as a comprehensive manual for the implementation of deep neural networks, including several architectures such as Multilayer Perceptron’s (MLPs), Convolutional Neural Networks (CNNs), Long Short-Term Memory networks (LSTMs), and others, inside the frameworks of Kera’s and TensorFlow. This book aims to serve as a concise resource for training and optimising deep neural networks. The book encompasses the foundational principles of neural networks, as well as the training methods used in deep neural networks. The book is highly recommended for students seeking a comprehensive reference manual on deep learning, as well as industry practitioners from many disciplines who want to embark on their data science endeavours.