Deep Learning with Python

De: Francois Chollet

Narrado por: Mark Thomas

Duración: 9 h y 55 m

Resumen del Editor

Deep Learning with Python introduces the field of deep learning using the Python language and the powerful Keras library. Written by Keras creator and Google AI researcher François Chollet, this audiobook builds your understanding through intuitive explanations and practical examples. You'll explore challenging concepts and practice with applications in computer vision, natural-language processing, and generative models. By the time you finish, you'll have the knowledge and hands-on skills to apply deep learning in your own projects. 

• Deep learning from first principles
• Setting up your own deep-learning environment
• Image-classification models
• Deep learning for text and sequences
• Neural style transfer, text generation, and image generation  

Machine learning has made remarkable progress in recent years. We went from near-unusable speech and image recognition, to near-human accuracy. We went from machines that couldn't beat a serious Go player, to defeating a world champion. Behind this progress is deep learning - a combination of engineering advances, best practices, and theory that enables a wealth of previously impossible smart applications.  

François Chollet works on deep learning at Google in Mountain View, CA. He is the creator of the Keras deep-learning library, as well as a contributor to the TensorFlow machine-learning framework. He also does deep-learning research, with a focus on computer vision and the application of machine learning to formal reasoning. His papers have been published at major conferences in the field, including the Conference on Computer Vision and Pattern Recognition (CVPR), the Conference and Workshop on Neural Information Processing Systems (NIPS), the International Conference on Learning Representations (ICLR), and others.

PLEASE NOTE: When you purchase this title, the accompanying PDF will be available in your Audible Library along with the audio.

©2017 Manning Publications Co. (P)2018 Manning Publications Co.

Supplimentary to the written version

The audio book is great if you also have a written version of it. I listened to this during my commute and caught up with the code examples later when I was with my laptop. This was a great book and the audio book was a great suppliment.

Outstanding Book

Great book and very easy to listen to while driving! Follow this author at @fchollet on Twitter...

ok for getting keywords

I halfway listened to this book to get the keywords of deep learning, and got that. However the book do a lot of referencing to tables, links and images which is difficult to follow when you dont have them in front of you.

Excellent Text as a Serious Introduction

Deep Learning with Python provides the required vocabulary, examples and overview to begin to understand how Python, Keras and TensorFlow are being used today to build predictive neural nets. I'm looking forward to François's followup text written for advanced programmers. The code examples are not read by the narrator, therefore the printed text is recommended as a support. A powerful way to retain this information is to read, then listen, then re-read, then re-listen to each chapter, following common guidelines for optimizing the interval between each visit. https://ncase.me/remember/ Part 2 "The Science of Spaced Repetition".

Almost Perfect - Better when paired with the book

Having such a technical book read aloud is awesome. And as far as the coverage of the subject matter, this is also fantastic as many Amazon reviewers will attest to. The only problem with the Audible version is that it was never intended to be used in isolation. The PDF that accompanies the Audible version contains numbered figures as well as some unnumbered code snippets. The problem is that many (maybe half) of the code snippets are missing from the PDF. For example the narrator will read the line "Finally, this was the training loop:", then he will ignore the code snippet and seamlessly continue with the next paragraph. You may not realize he is referring to some code, and even if you did, you would not know which code snippet because they are all unnumbered or simply missing form the PDF altogether. This is why this audio book is really only useful when paired with the eBook or physical book.

Great book, not the greatest voice recordings

The book is really well written and explained, but personally I found the voice to be monotone and a bit boring but I imagine that depends a lot on who's listening.

I also had other problems with the audio, including the fact that the narrator does not read which figure the text refers to, meaning he will just say "like this:" and not say which figure it is. This problem is compounded by the fact that the chapters in the PDF and the audiobook are offset from each other.

Very Good Book on the Topic

I'm sure it is challenging to write a book on this technical topic in the form of an audio book. The PDF file helped, but there were many times a url was referenced without speaking it or providing the url in the PDF file.

does not translate well to audiobook

it does a great job talking through complex material, but many concepts appear to be visual in nature. I believe this would be better ingested in a reading format.

Skip the Audible, buy the book

This is a good introduction to the subject of deep learning, but the audible format just doesn't suit it. He is constantly making references to illustrations. There is a PDF to download which contains most but not all of the illustrations. Also, he often references "this URL" in the audible but never specifies what the URL is. The accompanying PDF does not contain those URL references, at all, anywhere. Also, images on the PDF are such that they do not align with page breaks when printing. Thus images are split in half, with the top of the image on the bottom of one page, and the bottom of the image on the top of the next page. Overall a disapointingly sloppy implementation.

Don't get me wrong, I think this is a really good book. It is only valuable as an audible if you own the physical book and want it read to you. I am probably going to try to return it as an audible and purchase the physical book instead.