Deep learning is an artificial intelligence technology that enables computer vision, talk recognition in mobile phones, machine translation, AI games, driverless cars, and other applications. Whenever we make use of consumer items from Google, Microsoft, Facebook, Apple, or Baidu, we tend to be getting together with a deep learning program. In this volume in the MIT Press Necessary Knowledge series, computer scientist John Kelleher offers an accessible and concise but extensive introduction to the essential technology at the heart of the artificial intelligence revolution.

Kelleher explains some of the simple concepts in deep learning, presents a brief history of advancements in the field, and discusses the existing state from the artwork. He describes the most important deep learning architectures, including autoencoders, repeated neural systems, and long short-term networks, as well therefore recent developments as Generative Adversarial Networks and capsule networks. He also offers a extensive introduction to both fundamental algorithms in deep learning: gradient descent and backpropagation. Finally, Kelleher considers the continuing future of deep learning-major styles, possible advancements, and significant problems.