Introduction to Deep Learning
192 pp., 7 x 9 in, 75 b&w illus.
- Published: January 29, 2019
- Publisher: The MIT Press
- Published: February 19, 2019
- Publisher: The MIT Press
A project-based guide to the basics of deep learning.
This concise, project-driven guide to deep learning takes readers through a series of program-writing tasks that introduce them to the use of deep learning in such areas of artificial intelligence as computer vision, natural-language processing, and reinforcement learning. The author, a longtime artificial intelligence researcher specializing in natural-language processing, covers feed-forward neural nets, convolutional neural nets, word embeddings, recurrent neural nets, sequence-to-sequence learning, deep reinforcement learning, unsupervised models, and other fundamental concepts and techniques. Students and practitioners learn the basics of deep learning by working through programs in Tensorflow, an open-source machine learning framework. “I find I learn computer science material best by sitting down and writing programs,” the author writes, and the book reflects this approach.
Each chapter includes a programming project, exercises, and references for further reading. An early chapter is devoted to Tensorflow and its interface with Python, the widely used programming language. Familiarity with linear algebra, multivariate calculus, and probability and statistics is required, as is a rudimentary knowledge of programming in Python. The book can be used in both undergraduate and graduate courses; practitioners will find it an essential reference.
“We have a choice of a variety of books on deep learning: books on the theory written by expert academics, and practical books written by programmers. This book gives you the best of both: Charniak is a prominent academic researcher who has been through every phase of artificial intelligence, often as a leader in ushering in a new phase. And he remains an active programmer who understands by doing. In this masterfully executed book he shows you what he has come to understand, allowing you to follow the code step by step, and also learn from his informed conclusions.”
Peter Norvig, Research Director, Google
“A wonderful book filling the yawning gap between the existing comprehensive 'bible' (by Goodfellow, Bengio, and Courville) and the many books aimed at industry practitioners. This approachable volume provides clear, engaging writing describing the theory and practical implementation of the key deep learning algorithms across vision, NLP, and robotics. The carefully thought out, compact presentation gets surprisingly close to the current state-of-the-art in deep learning, making it an ideal textbook for students and others seeking an insightful introduction to deep learning.”
Chris Manning, Professor of Computer Science and Linguistics, Stanford University
“Deep learning is a mainstream tool in artificial intelligence and machine learning. This introductory text prepares a beginner for entering this exciting area of deep learning.”
Dapeng Oliver Wu, Professor of Computer Science, University of Florida
“Eugene Charniak is famous for his clear explanations of important but complicated topics in artificial intelligence. In this book, he illuminates deep learning, introducing the essential building blocks for those who want a thorough, intuitive, hands-on, and hype-free experience. It will be highly valuable for practitioners and students alike.”
Noah A. Smith, Associate Professor of Computer Science, University of Washington