Deep Learning

MIT Press Essential Knowledge Series

De: John D. Kelleher

Narrado por: Joel Richards

Deep learning is an artificial intelligence technology that enables computer vision, speech recognition in mobile phones, machine translation, AI games, driverless cars, and other applications. When we use consumer products from Google, Microsoft, Facebook, Apple, or Baidu, we are often interacting with a deep learning system. In this volume in the MIT Press Essential Knowledge series, computer scientist John Kelleher offers an accessible and concise but comprehensive introduction to the fundamental technology at the heart of the artificial intelligence revolution.

Kelleher explains some of the basic concepts in deep learning, presents a history of advances in the field, and discusses the current state of the art. He describes the most important deep learning architectures, including autoencoders, recurrent neural networks, and long short-term networks, as well as such recent developments as Generative Adversarial Networks and capsule networks. He also provides a comprehensive introduction to the two fundamental algorithms in deep learning: gradient descent and backpropagation. Finally, Kelleher considers the future of deep learning-major trends, possible developments, and significant challenges.

©2019 Massachusetts Institute of Technology (P)2019 Gildan Media

very good book

the book a gives a comprehensive introduction, I needed two days to finish as it is very clear and direct to the point.

Very understandable explanations

This was an excellent introductory book on deep learning. The author has a gift for explaining the material well.

Great book

Great book. It was well read. It does have equations and charts/figures that the reader refers to. The equation are not too bad, but if you’re not familiar with either calculus or higher level math or formal logic, following the narration of the equations might be a bit difficult. Overall, 8/10 recommend it.

ass kicking good

this book is over my head and I love it. very technical and granular, but still aimed at beginners.

Inexperienced narrator on the field

This book is unlike normal books. You simply cannot proficiently read a book filled with images and formulas on such a technical subject without having a thorough understanding of the content. The narrator, unfortunately, and very clearly, has absolutely no idea of what he's reading. The way he over-describes formulas and under-describes images (or worse, doesn't describe at all, no matter how simple) makes you require to go back and forth between written book more often than would be desired.

As for the book itself, I'm really enjoying the overview this gives on the subject. I bought it alongside the kindle version, and if you must get this narration, please get the printed version as well so you're able to follow what's being said.

Good performance, but probably need the text to fully grasp what is going on

I like listening to audiobooks for different reasons. One reason is to help push me through challenging or new material. In these cases, I find it helpful to have the text in front of me as it’s being read.

This book does have a lot of equations, but it was especially helpful to have the narrator explaining what was going on in complex diagrams so I didn’t have to keep flipping back and forth between the text and the figures.

Yikes

This is pretty much unintelligible. About half of it is the guy reading off equations so slowly that it’s impossible (for me anyway) to picture what he’s saying. “Right bracket x sub zero equals open parentheses a plus b smaller parentheses y sub 1 close small parentheses....” come on man nobody thinks like that