Computer Science

Deep Learning with Python

Deep Learning with Python

  • Downloads：5611
  • Type：Epub+TxT+PDF+Mobi
  • Create Date：2021-10-27 09:51:49
  • Update Date：2025-09-06
  • Status：finish
  • Author：François Chollet
  • ISBN：1617296864
  • Environment：PC/Android/iPhone/iPad/Kindle
  • Download

Summary

In Deep Learning with Python， Second Edition， updated from the original bestseller with over 50% new content， you'll explore challenging concepts and practice applications in computer vision， natural-language processing， and generative models。

The bestseller revised！ Deep Learning with Python， Second Edition is a comprehensive introduction to the field of deep learning using Python and the powerful Keras library， written by the creator of Keras himself。 This revised edition has been updated with new chapters， new tools， and cutting-edge techniques drawn from the latest research。

In Deep Learning with Python， Second Edition， updated from the original bestseller with over 50% new content， you'll explore challenging concepts and practice applications in computer vision， natural-language processing， and generative models， building your understanding through practical examples and intuitive explanations that make the complexities of deep learning easily accessible。

Purchase of the print book includes a free eBook in PDF， Kindle， and ePub formats from Manning Publications。

Download

Reviews

Joseph Yao ，

This is a book for data science practitioners。 It covers many examples about how to develop a deep learning model from scratch using Keras， a high level API of tensorflow。 You can even train your first language generation model to write a poem in the language of Shakespeare or use neural style transfer to create painting with a mix of Van Gogh's and Picasso's style。 This book tells you how to achieve them。 This is a book for data science practitioners。 It covers many examples about how to develop a deep learning model from scratch using Keras， a high level API of tensorflow。 You can even train your first language generation model to write a poem in the language of Shakespeare or use neural style transfer to create painting with a mix of Van Gogh's and Picasso's style。 This book tells you how to achieve them。 。。。more

Ryan ，

Covers exactly what it needed to with great examples。 For an intermediate python user like myself some more explanation or expected outputs could have been useful but still easy enough to follow。

Adri Molina ，

If you're a STEM student and you want to learn to program deep learning without struggling too much with algorithms and maths this is the book。Straightforward tutorials with understandable and high level code with a low or inexistent programming knowledge barrier。 Probably the best hands-on approach for deep learning introduction。The explanations are quite updated and it teaches almost every kind of deep learning algorithm you should expect to know as introduction。 Despite being an introduction If you're a STEM student and you want to learn to program deep learning without struggling too much with algorithms and maths this is the book。Straightforward tutorials with understandable and high level code with a low or inexistent programming knowledge barrier。 Probably the best hands-on approach for deep learning introduction。The explanations are quite updated and it teaches almost every kind of deep learning algorithm you should expect to know as introduction。 Despite being an introduction the topics are diverse enough to consider this a wide perspective of the deep learning capabilities。 。。。more

Ramasubramaniam ，

Excellent。 Not sure it will stand test of time。 As long as python rules this book will rule！！

Tim ，

intro explains the why。 doesn't just jump into it。 intro explains the why。 doesn't just jump into it。 。。。more

Yuki ，

I think this book is really great for those who are new to this area。 Really easy to understand。

Stein Karlsen ，

Great book on deep learning， with good examples of the models discussed。 I really enjoyed the discussions around when specific architecture and techniques were appropriate。

PJ ，

Simple， clear overview of deep learning/neural networks with important considerations for its applications to real world problems。 Gets you up to speed with the concepts in no time。

Chris Esposo ，

It’s hard to get a book “closer-to-the-metal” in applied deep learning than one written by the author of Keras， but that’s exactly what this book is， and it delivers the content extremely well。 I listened to the book both in audio format， and probably have gone through 40 - 50% of the book via physical reading， and found the audio delivery was a better channel than I expected， given that this is effectively a programming text， but still was no cigar compared to an actual reading。 The better-than It’s hard to get a book “closer-to-the-metal” in applied deep learning than one written by the author of Keras， but that’s exactly what this book is， and it delivers the content extremely well。 I listened to the book both in audio format， and probably have gone through 40 - 50% of the book via physical reading， and found the audio delivery was a better channel than I expected， given that this is effectively a programming text， but still was no cigar compared to an actual reading。 The better-than-expected delivery via audio probably has much to do with how much of the book is dedicated not to a software or technical treatment of instrumenting the neural networks， but to the history of machine learning in general， as well as a conceptual overview of the basic machine learning pipeline。 Roughly 50 pages of the first 4 chapters （or about half of the page-count for those chapters） is dedicated to this conceptual treatment of machine learning， the first chapter being a history of shallow-learning that led up to the advent of the first neural network， it’s failure in the early 90s， the emergence of both kernel methods and ensembling as a the predominant paradigm， then finally the reemergence of neural networks within the framework of GPU-backed deep neural networks （DNNs）， The 4th chapter goes through the standard ML pipeline （model-estimation， train/test， tuning and performance tracking via cross-validation etc。， which is almost entirely independent of DNN as a conceptual framework。 These 2 chapters are easily digestible via audio。 Chapters 2 and 3， which discusses the rudiments of neural networks conceptually and how to navigate Kera’s internal API are also pretty light-weight in terms of technical content and also are easily digestible via audio。 Thus， slightly above a ⅓ of the text is well-written for audio。 Where the text becomes troublesome for the audio reader is from chapter 5 onward， where step-by-step code templates for DNNs written within Keras are presented for the two major domain-areas computer vision and text/language。 These chapters in my opinion are where the real value of the text lay as they include not only the cookie-cutter basic nets for a set of use-cases within each domain， but there’s a lot of commentary on how design-features （adding/subtracting hidden-layers， where to regularize/drop-out， where to pool etc。） a person may customize in their own net may impact the performance of that use-case in the domain。 Going through these chapters carefully can quickly get someone to implement （at least with decent performance）。That being said， the templates are all fairly simple， and more recent innovations like multi-task and other bifurcating network topologies do not make it into the material in any substantial （or at all） manner。 Though， it should be remembered this is a first-pass book， and was written in 2015-16 （published in 17/18’ depending on the format）， and so this can be excused。 Overall， the level of content is decidedly more from the practitioner’s standpoint， which is appropriate for this subfield in machine learning， since a full rigorous treatment of the mathematical properties of NNs still mostly elusive， with the theory currently being constructed， this field should be more of a software engineering domain。 In fact， Andrew Ng himself has often stated that the best way to learn NNs is to do NNs， and this book will have you implementing NNs within the first 2 - 3 hours of reading。 This was not the first treatment of the material I’ve gone through， having done most of Ng’s Coursera courses， and other academic material， and having attended some seminars on the the theoretical treatment of the subject also in an academic context （mostly， understanding NNs within the context of universal approximation）， as well as deploying some in work， I still found the book to be useful， and will reference it at least for a little while longer。 There’s a chapter on best-practices within the Keras API， and I suspect there is some value for even intermediate users of these objects in sections of the text like this， as well as the aforementioned code template-sections。 Overall， I enjoyed this book， and recommend it highly （especially for newer practitioners or students of the subject matter）。 It seems like it would pair well with Goodellow et。 al。， and I've seen both of these books required as textbooks in sync in some syllabi for standard graduate courses on the subject。 。。。more

Clancy Birrell ，

Excellent！Readable， practical， sensible， insightful and relevant。For anyone wanting a great reasonable depth practical introduction to deep learning you would do well to start here。

Arian Beckmann ，

Excellent book。 Can recommend to anybody who has previous experience with Python and Deep Learning and wants to learn the structure of the Keras framework。

Bilge ，

Türkçesin’i değil ama İngilizcesini tavsiye ederim

Mukharbek Organokov， PhD ，

Very good book。 I like it。

Javier García ，

This is absolutely not a book for beginners。 It's very good if you know the theoretical concepts of deep learning and you want to know how to implement them on Keras。 Otherwise you're going to feel lost。 I recommend first taking the Andrew Ng course， it will help a lot， and maybe after that reading this book。 This is absolutely not a book for beginners。 It's very good if you know the theoretical concepts of deep learning and you want to know how to implement them on Keras。 Otherwise you're going to feel lost。 I recommend first taking the Andrew Ng course， it will help a lot， and maybe after that reading this book。 。。。more

Martin ，

Very good introduction with lots of example code and not too much math。 However， I felt that the core concepts are introduced very briefly and not explained very much。 I would say that this book takes the approach of "this is what you need to know to get started using Keras" and gives you just the intuitive understanding of each area。 If you just want to try deep learning on some datasets， this is a good book to start doing just that。 If you are new to AI/ML， I would recommend getting some more Very good introduction with lots of example code and not too much math。 However， I felt that the core concepts are introduced very briefly and not explained very much。 I would say that this book takes the approach of "this is what you need to know to get started using Keras" and gives you just the intuitive understanding of each area。 If you just want to try deep learning on some datasets， this is a good book to start doing just that。 If you are new to AI/ML， I would recommend getting some more rigorous introduction first - at the end of the day， you will need the math to understand the results you are getting。 。。。more

Mèo lười ，

Quyển này chính là Dế mèn phiêu lưu kí trong deep learning =，= nhẹ nhàng， dễ hiểu， dễ tưởng tượng。Hiuhiu。

Elvin Ugonna ，

Wonderful book to lay hands on

Alexandru Voda ，

Very concise and practical。 Does exactly what the title suggests: gives an overview of DL implementations in Python & Keras。 Great， crystal-clear coding examples that ran just fine for myself。 For a mathematical understanding of DL， you'd have to go and read a book specialised on that， take courses or start by watching the play lists made by 3blue1brown on YouTube years ago。 Very concise and practical。 Does exactly what the title suggests: gives an overview of DL implementations in Python & Keras。 Great， crystal-clear coding examples that ran just fine for myself。 For a mathematical understanding of DL， you'd have to go and read a book specialised on that， take courses or start by watching the play lists made by 3blue1brown on YouTube years ago。 。。。more

Moustafa ，

Great bool

Tolu O。 ，

Incredibly written and really insightful book。 Definitely getting a physical copy and keeping this for future reference。

Ankur Chawla ，

It seems the many writers are loosing there the intellect to write over the year。 i hope there are more writers like this in today's world。。。 However， beautiful detailed crisp description and portrayal of the great Shivaji。 Many people might not have the right understanding of the person or the subject and this books clears the cloud and provides a very clear understanding on that。 Great to have come across this book。 very nice read。。。。 It seems the many writers are loosing there the intellect to write over the year。 i hope there are more writers like this in today's world。。。 However， beautiful detailed crisp description and portrayal of the great Shivaji。 Many people might not have the right understanding of the person or the subject and this books clears the cloud and provides a very clear understanding on that。 Great to have come across this book。 very nice read。。。。 。。。more

Jose Luis Calvo Salanova ，

Muy buena introducción a las redes neuronales con keras。 Obvia la parte matemática， que por un lado simplifica y por otro en algún momento puede parecer magia。 Recomendable para cualquier programador。

Adrián Domínguez ，

Extraordinary book to learn the fundamentals of deep learning with a practical approach。

Philipda Luangprasert ，

This is the guide to deep learning using Keras， the most popular tool， from the creator himself。It provides advanced introduction without dealing with complicated stuffs （math， tensorflow， etc。）。 Although it is also good for starters， it is not the best choice to jump in without some prior knowledge。 As he said in the book， starters may tempt to think that "all you have is [a powerful， easy， black-boxed] deep-learning hammer， and every problem starts to look like a nail。" This is the guide to deep learning using Keras， the most popular tool， from the creator himself。It provides advanced introduction without dealing with complicated stuffs （math， tensorflow， etc。）。 Although it is also good for starters， it is not the best choice to jump in without some prior knowledge。 As he said in the book， starters may tempt to think that "all you have is [a powerful， easy， black-boxed] deep-learning hammer， and every problem starts to look like a nail。" 。。。more

Gerrit Luimstra ，

Gorgeously written and provides a lot of practical examples。 Provides a high level but thorough walkthrough of the theoretical aspects of the models presented。

Johnny ，

A great book that explains the various parts of deep learning with Python。 There could have a bit more explanation on the reasoning behind the chosen approaches， but otherwise it covers everything you need to know。

bimri ，

Best generalization of AI precepts I could find。 Well written & simple to follow through all DL abstractions。

Israel ，

Quick note I want to make before I proceed with this review:I decided to try something new and bought the audiobook version of this book， making this my first "software"-related audiobook。 If you decide to listen to the audiobook， the audiobook also comes with a PDF file as a "follow along" document which contains examples， figures， and charts for each of the chapters。Overall， the audiobook and accompanying PDF document works really well as a format for this subject matter。 This is a helpful and Quick note I want to make before I proceed with this review:I decided to try something new and bought the audiobook version of this book， making this my first "software"-related audiobook。 If you decide to listen to the audiobook， the audiobook also comes with a PDF file as a "follow along" document which contains examples， figures， and charts for each of the chapters。Overall， the audiobook and accompanying PDF document works really well as a format for this subject matter。 This is a helpful and practical book which shows how to create various machine learning frameworks with Python and Keras。 These frameworks are used for different applications such as in: computer vision， natural language processing （NLP）， binary/multiple classification（s）， etc。 I learned some helpful methods and algorithms to use for Keras， and reviewed some material that I learned beforehand （particularly for classification techniques and convolutional networks）。 Whether you are new to machine learning or are an active practitioner， this is a great resource to have in your library。 。。。more

Bilal ，

Excellent book to get a quick start on deep learning！ This is not a book to learn the theoretical aspects of deep-learning， rather it is a collection of hands-on examples to work through and learn by experience and the guidance provided by the author。 That said， if you have seen neural networks from the 1990s along with the back propagation algorithm， and you can visualize the concepts of gradient descent and convolution， then this material is very easy to followThe examples are setup on the Ker Excellent book to get a quick start on deep learning！ This is not a book to learn the theoretical aspects of deep-learning， rather it is a collection of hands-on examples to work through and learn by experience and the guidance provided by the author。 That said， if you have seen neural networks from the 1990s along with the back propagation algorithm， and you can visualize the concepts of gradient descent and convolution， then this material is very easy to followThe examples are setup on the Keras framework using TensorFlow as the backend engine。 I used an EC2 p2。xlarge instance as suggested by the author。 The setup required a bit of help beyond what's provided in Appendix B。 Once setup though you will need to run from a virtual environment: "source activate tensorflow_p36"。 。 。 。 。 。 My final thought is that after having read Chapter 7， I want to do a second pass using callbacks and tensorboard for better insight。 。。。more

Ewan ，

The perfect practical introduction to DL， it doesn't claim to be a mathematical explanation of DL and it doesn't get bogged down in maths。 Instead it gives lots of examples and explains in intuitive ways the implementation where necessary。 The perfect practical introduction to DL， it doesn't claim to be a mathematical explanation of DL and it doesn't get bogged down in maths。 Instead it gives lots of examples and explains in intuitive ways the implementation where necessary。 。。。more

Reference

google book https://www.google.com/search?tbm=bks&q=Deep Learning with Python

hathitrust digital library https://babel.hathitrust.org/cgi/ls?q1=Deep Learning with Python&field1=ocr&a=srchls&ft=ft&lmt=ft

The British Library https://bll01.primo.exlibrisgroup.com/discovery/search?query=any,contains,Deep Learning with Python&tab=LibraryCatalog&search_scope=Not_BL_Suppress&vid=44BL_INST:BLL01&lang=en&offset=0