Deep learning is a group of exciting new technologies for neural networks. Through advanced training techniques and neural network architectural components, it is now possible to create neural networks that can handle tabular data, images, text, and audio as both input and output. Deep learning allows a neural network to learn information hierarchies like the human brain’s function. This book will introduce the student to classic neural network structures, Convolution Neural Networks (CNN), Transformers, Long Short-Term Memory (LSTM), Gated Recurrent Neural Networks (GRU), General Adversarial Networks (GAN), and reinforcement learning.
This book covers the application of these architectures to computer vision, time series, security, natural language processing (NLP), and data generation. The book presents both GPU and CPU processing for deep learning. The focus is primarily on applying deep learning to problems and introducing mathematical foundations as needed. Students will use the Python programming language to implement deep learning using Google TensorFlow and Keras. Some applications make use of PyTorch.
All code and text from this book are available from the author's GitHub repository.
