Deep Learning Audiobook (Free)

Deep learning can be an artificial intelligence technology that allows computer vision, talk recognition in mobile phones, machine translation, AI games, driverless cars, and other applications. When we use consumer items from Google, Microsoft, Facebook, Apple, or Baidu, we tend to be interacting with a deep learning program. In this volume in the MIT Press Necessary Knowledge series, computer scientist John Kelleher offers an available and concise but comprehensive introduction to the essential technology in the centre from the artificial cleverness revolution.

Kelleher explains a number of the fundamental ideas in deep learning, presents a brief history of improvements in the field, and discusses the current state from the art. He describes the most important deep learning architectures, including autoencoders, recurrent neural systems, and lengthy short-term networks, as well therefore recent developments as Generative Adversarial Systems and capsule networks. He also provides 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 developments, and significant difficulties.