Amazon Prime Free Trial
FREE Delivery is available to Prime members. To join, select "Try Amazon Prime and start saving today with FREE Delivery" below the Add to Cart button and confirm your Prime free trial.
Amazon Prime members enjoy:- Cardmembers earn 5% Back at Amazon.com with a Prime Credit Card.
- Unlimited FREE Prime delivery
- Streaming of thousands of movies and TV shows with limited ads on Prime Video.
- A Kindle book to borrow for free each month - with no due dates
- Listen to over 2 million songs and hundreds of playlists
Important: Your credit card will NOT be charged when you start your free trial or if you cancel during the trial period. If you're happy with Amazon Prime, do nothing. At the end of the free trial, your membership will automatically upgrade to a monthly membership.
Download the free Kindle app and start reading Kindle books instantly on your smartphone, tablet, or computer - no Kindle device required.
Read instantly on your browser with Kindle for Web.
Using your mobile phone camera - scan the code below and download the Kindle app.
Follow the author
OK
Understanding Deep Learning
Purchase options and add-ons
Deep learning is a fast-moving field with sweeping relevance in today’s increasingly digital world. Understanding Deep Learning provides an authoritative, accessible, and up-to-date treatment of the subject, covering all the key topics along with recent advances and cutting-edge concepts. Many deep learning texts are crowded with technical details that obscure fundamentals, but Simon Prince ruthlessly curates only the most important ideas to provide a high density of critical information in an intuitive and digestible form. From machine learning basics to advanced models, each concept is presented in lay terms and then detailed precisely in mathematical form and illustrated visually. The result is a lucid, self-contained textbook suitable for anyone with a basic background in applied mathematics.
- Up-to-date treatment of deep learning covers cutting-edge topics not found in existing texts, such as transformers and diffusion models
- Short, focused chapters progress in complexity, easing students into difficult concepts
- Pragmatic approach straddling theory and practice gives readers the level of detail required to implement naive versions of models
- Streamlined presentation separates critical ideas from background context and extraneous detail
- Minimal mathematical prerequisites, extensive illustrations, and practice problems make challenging material widely accessible
- Programming exercises offered in accompanying Python Notebooks
- ISBN-100262048647
- ISBN-13978-0262048644
- PublisherThe MIT Press
- Publication dateDecember 5, 2023
- LanguageEnglish
- Dimensions8.25 x 1.44 x 9.31 inches
- Print length544 pages
Frequently bought together
More items to explore
Editorial Reviews
About the Author
Product details
- Publisher : The MIT Press (December 5, 2023)
- Language : English
- Hardcover : 544 pages
- ISBN-10 : 0262048647
- ISBN-13 : 978-0262048644
- Item Weight : 2.95 pounds
- Dimensions : 8.25 x 1.44 x 9.31 inches
- Best Sellers Rank: #30,366 in Books (See Top 100 in Books)
- #11 in Computer Neural Networks
- #62 in Internet & Social Media
- #93 in Artificial Intelligence & Semantics
- Customer Reviews:
About the author
Dr Simon J.D. Prince is a faculty member in the Department of Computer Science at University College London. He has taught courses on machine vision, image processing, and advanced mathematical methods. He has a diverse background in biological and computing sciences and has published papers across the fields of computer vision, biometrics, psychology, physiology, medical imaging, computer graphics, and HCI.
Customer reviews
- 5 star4 star3 star2 star1 star5 star93%4%0%0%3%93%
- 5 star4 star3 star2 star1 star4 star93%4%0%0%3%4%
- 5 star4 star3 star2 star1 star3 star93%4%0%0%3%0%
- 5 star4 star3 star2 star1 star2 star93%4%0%0%3%0%
- 5 star4 star3 star2 star1 star1 star93%4%0%0%3%3%
Customer Reviews, including Product Star Ratings help customers to learn more about the product and decide whether it is the right product for them.
To calculate the overall star rating and percentage breakdown by star, we don’t use a simple average. Instead, our system considers things like how recent a review is and if the reviewer bought the item on Amazon. It also analyzed reviews to verify trustworthiness.
Learn more how customers reviews work on AmazonCustomers say
Customers find the book a great resource for understanding deep learning concepts. They find the writing style easy to follow and intuitive, with clear explanations and top-level illustrations. The book is described as friendly to beginners with good printing quality.
AI-generated from the text of customer reviews
Customers appreciate the book's knowledge level. They find it a great resource for understanding deep learning concepts, with valuable information and good resources for all levels. The visuals and intuition are appreciated.
"...Takes a long time to digest but the knowledge is priceless." Read more
"This book is a great resource to understand the concepts behind deep learning...." Read more
"this text makes Deep Learning much more accessible without spending time on proofs and theorems...." Read more
"...Visualizations and intuition are pleasing. Many foundation and recent topics covered with in-depth understanding...." Read more
Customers find the book easy to understand and approachable. The writing style is straightforward and well-explained, making it a good book for beginners.
"...The writing style is easy to follow and the flow of each chapter is intuitive. The best book on DL to cut through the noise!..." Read more
"While the math is not sophisticated, it is used very well to explain the material...." Read more
"a very good book friendly to beginer easy to understand good printing quality" Read more
"Super approachable..." Read more
Customers appreciate the book's visuals. They find the illustrations clear and detailed, but not overly wordy.
"...math to understand the concepts explained, and the illustrations are top-level. All exercises in the book serve a purpose." Read more
"...It is great to have a hard copy of an up to date text book. Love the visuals and equations provided and also the very detailed but not over winded..." Read more
"As a seasoned practitioner, I recommend this book as a must-have. Visualizations and intuition are pleasing...." Read more
Reviews with images
Excellent resources for all levels
Top reviews from the United States
There was a problem filtering reviews right now. Please try again later.
- Reviewed in the United States on May 27, 2024I recently finished my masters in bioengineering and while i learned a lot of mathermatical
principles and some novel computational modeling skills, we did not touch on deep learning. This book has been just an excellent resource in building this foundation - granted it does help to have a background in multi variate calculus and statistics, but this book tells you everything you need to know.
The writing style is easy to follow and the flow of each chapter is intuitive. The best book on DL to cut through the noise! Also recommend going through the python notebooks. The author was kind enough to send me the answers to the notebook as i’m just self studying not in a class.
Looking forward to the next addition!
5.0 out of 5 stars Excellent resources for all levelsI recently finished my masters in bioengineering and while i learned a lot of mathermatical
Reviewed in the United States on May 27, 2024
principles and some novel computational modeling skills, we did not touch on deep learning. This book has been just an excellent resource in building this foundation - granted it does help to have a background in multi variate calculus and statistics, but this book tells you everything you need to know.
The writing style is easy to follow and the flow of each chapter is intuitive. The best book on DL to cut through the noise! Also recommend going through the python notebooks. The author was kind enough to send me the answers to the notebook as i’m just self studying not in a class.
Looking forward to the next addition!
Images in this review - Reviewed in the United States on November 30, 2024What a great book I wish I was smart enough to understand it! Takes a long time to digest but the knowledge is priceless.
- Reviewed in the United States on July 10, 2024This book is a great resource to understand the concepts behind deep learning. The author uses only the necessary math to understand the concepts explained, and the illustrations are top-level. All exercises in the book serve a purpose.
- Reviewed in the United States on October 13, 2024While the math is not sophisticated, it is used very well to explain the material. I've read several descriptions of transformers and this was the only one I understood. The notes after each chapter are also quite good.
- Reviewed in the United States on September 10, 2024This is an excellent book for people like me who don't have a strong math background. I read the other popular deep learning book by Goodfellow, and I struggled to follow
- Reviewed in the United States on June 29, 2024this text makes Deep Learning much more accessible without spending time on proofs and theorems. The author doesn't try to stretch the "neuron" analogy to the point of being silly like many similar texts
- Reviewed in the United States on February 29, 2024I think this is a fantastic book. It is great to have a hard copy of an up to date text book. Love the visuals and equations provided and also the very detailed but not over winded explanations.
- Reviewed in the United States on March 4, 2024This is an excellent book if you're looking to get into Deep Learning, the examples and explanations are comprehensive and the book as a whole provides a great jump-off point for exploring the field.
Top reviews from other countries
-
Eduardo Hiroshi NakamuraReviewed in Brazil on July 23, 2024
1.0 out of 5 stars Ruim
Infelizmente com exemplos em Python.
- Ashkan DehghanReviewed in Canada on January 29, 2024
5.0 out of 5 stars Love the book
Why I love this book:
One of the reasons I love this book is the combination of clear writing and explanation in combination with well thoughtful illustrations. Having great illustrations can bring a new dimension in understanding a new concept and this book does this really well. Second, is the collection of "author's notes" at the end of each chapter. Providing references and insights into current (as of 2022) research, references and so on. I have used many of the references at the end of each chapter to dig deeper into a particular topic. Lastly, mathematical equations are used to give insight into a concept, rather than giving an illusion that a concept is more complex than it needs to be.
Who I think this book is for:
I think whether you are a seasoned ML researcher or a student, you can benefit from this book to learn about subjects and concepts that are not directly related to your field. This book can act as a great primer, to be used with more detailed papers/books to fully understand a given subject.
Who I think this book is NOT for:
I think if you are looking for a very detailed or mathematics heavy text on deep-learning (or some architecture) then this book is not for you. For example, if you already work with Transformers and have a good understanding of them, this book wont teach you something you dont already know. So dont expect it to be a detailed overview of any particular subject.
Overall, I think anyone who does machine-learning should own a copy of this book. For me, it is worth every dollar.
- Nikhil KapilaReviewed in the United Arab Emirates on October 16, 2024
5.0 out of 5 stars Great visuals and amazing book.
This book has a lot of visuals and goes into the depths of the concepts. Highly recommend to gain intuition to common DL topics!
Plus, the author has a website with all code examples which is really helpful.
- Jens HoveReviewed in Germany on October 15, 2024
5.0 out of 5 stars Excellent book
Comprehensive overview
- ALBAReviewed in Italy on May 29, 2024
5.0 out of 5 stars To start with Deep Learning
This is an extremely well-written reference to start grasping knowledge behind Deep Learning programming techniques. Contents are mainly devoted to unwrapping the complex theoretical background, essentially mathematical tools and techniques useful to develop a neural network (the book has appendices that further explain concepts from linear algebra and vector calculus). Exercises and Jupyter Notebook are freely available on the GitHub repository of the book, search for Simon Prince's GitHub, and you will get insight into practical Python programming exercises. Overall, great introductory textbooks for this topic!