the Nest of Students

Natural Language Processing (NLP) is a sub-field of Artificial Intelligence, linguistics, and computer science and is concerned with the generation, recognition, and understanding of human languages, both written and spoken. NLP systems examine the grammatical structure of sentences as well as the specific meanings of words, and then they utilize algorithms to extract meaning and produce results. Machine Learning and Deep Learning in Natural Language Processing aims at providing a review of current Neural Network techniques in the NLP field, in particular about Conversational Agents (chatbots), Text-to-Speech, management of non-literal content – like emotions, but also satirical expressions – and applications in the healthcare field.

NLP has the potential to be a disruptive technology in various healthcare fields, but so far little attention has been devoted to that goal. This book aims at providing some examples of NLP techniques that can, for example, restore speech, detect Parkinson’s disease, or help psychotherapists. This book is intended for a wide audience. Beginners will find useful chapters providing a general introduction to NLP techniques, while experienced professionals will appreciate the chapters about advanced management of emotion, empathy, and non-literal content.

This book covers both classical and modern models in deep learning. The primary focus is on the theory and algorithms of deep learning. The theory and algorithms of neural networks are particularly important for understanding important concepts, so that one can understand the important design concepts of neural architectures in different applications. Why do neural networks work? When do they work better than off-the-shelf machine-learning models? When is depth useful? Why is training neural networks so hard? What are the pitfalls? The book is also rich in discussing different applications in order to give the practitioner a flavor of how neural architectures are designed for different types of problems. Applications associated with many different areas like recommender systems, machine translation, image captioning, image classification, reinforcement-learning based gaming, and text analytics are covered. The chapters of this book span three categories:

The basics of neural networks: Many traditional machine learning models can be understood as special cases of neural networks. An emphasis is placed in the first two chapters on understanding the relationship between traditional machine learning and neural networks. Support vector machines, linear/logistic regression, singular value decomposition, matrix factorization, and recommender systems are shown to be special cases of neural networks. These methods are studied together with recent feature engineering methods like word2vec. Fundamentals of neural networks: A detailed discussion of training and regularization is provided in Chapters 3 and 4. Chapters 5 and 6 present radial-basis function (RBF) networks and restricted Boltzmann machines. Advanced topics in neural networks: Chapters 7 and 8 discuss recurrent neural networks and convolutional neural networks. Several advanced topics like deep reinforcement learning, neural Turing machines, Kohonen self-organizing maps, and generative adversarial networks are introduced in Chapters 9 and 10.

The book is written for graduate students, researchers, and practitioners. Numerous exercises are available along with a solution manual to aid in classroom teaching. Where possible, an application-centric view is highlighted in order to provide an understanding of the practical uses of each class of techniques.

Deep learning is one of today’s hottest fields. This approach to machine learning is achieving breakthrough results in some of today’s highest profile applications, in organizations ranging from Google to Tesla, Facebook to Apple. Thousands of technical professionals and students want to start leveraging its power, but previous books on deep learning have often been non-intuitive, inaccessible, and dry. In Deep Learning Illustrated, three world-class instructors and practitioners present a uniquely visual, intuitive, and accessible high-level introduction to the techniques and applications of deep learning. Packed with vibrant, full-color illustrations, it abstracts away much of the complexity of building deep learning models, making the field more fun to learn, and accessible to a far wider audience.

Part I’s high-level overview explains what Deep Learning is, why it has become so ubiquitous, and how it relates to concepts and terminology such as Artificial Intelligence, Machine Learning, Artificial Neural Networks, and Reinforcement Learning. These opening chapters are replete with vivid illustrations, easy-to-grasp analogies, and character-focused narratives. Building on this foundation, the authors then offer a practical reference and tutorial for applying a wide spectrum of proven deep learning techniques. Essential theory is covered with as little mathematics as possible, and illuminated with hands-on Python code. Theory is supported with practical “run-throughs” available in accompanying Jupyter notebooks, delivering a pragmatic understanding of all major deep learning approaches and their applications: machine vision, natural language processing, image generation, and videogaming. To help readers accomplish more in less time, the authors feature several of today’s most widely-used and innovative deep learning libraries, including TensorFlow and its high-level API, Keras; PyTorch, and the recently-released high-level Coach, a TensorFlow API that abstracts away the complexity typically associated with building Deep Reinforcement Learning algorithms.

Generative modeling is one of the hottest topics in AI. It’s now possible to teach a machine to excel at human endeavors such as painting, writing, and composing music. With this practical book, machine-learning engineers and data scientists will discover how to re-create some of the most impressive examples of generative deep learning models, such as variational autoencoders,generative adversarial networks (GANs), encoder-decoder models, and world models.

Author David Foster demonstrates the inner workings of each technique, starting with the basics of deep learning before advancing to some of the most cutting-edge algorithms in the field. Through tips and tricks, you’ll understand how to make your models learn more efficiently and become more creative. Discover how variational autoencoders can change facial expressions in photos + Build practical GAN examples from scratch, including CycleGAN for style transfer and MuseGAN for music generation + Create recurrent generative models for text generation and learn how to improve the models using attention + Understand how generative models can help agents to accomplish tasks within a reinforcement learning setting + Explore the architecture of the Transformer (BERT, GPT-2) and image generation models such as ProGAN and StyleGAN.

Take the next steps toward mastering deep learning, the machine learning method that’s transforming the world around us by the second. In this practical book, you’ll get up to speed on key ideas using Facebook’s open source PyTorch framework and gain the latest skills you need to create your very own neural networks. Ian Pointer shows you how to set up PyTorch on a cloud-based environment, then walks you through the creation of neural architectures that facilitate operations on images, sound, text,and more through deep dives into each element. He also covers the critical concepts of applying transfer learning to images, debugging models, and PyTorch in production.