Buy new:

$39.99

FREE Returns

FREE delivery Tuesday, February 14

Or fastest delivery February 10 - 13

In Stock.

[{"displayPrice":"$39.99","priceAmount":39.99,"currencySymbol":"$","integerValue":"39","decimalSeparator":".","fractionalValue":"99","symbolPosition":"left","hasSpace":false,"showFractionalPartIfEmpty":true,"offerListingId":"m8sNA9rV1LvoFbnNqT2WH5i6lcyS1e1tAm0HDHEw1lcFm%2F1oYs9pHdLv75IHCZEW9bO%2BM4ikuQedLUcpGxjyNgcOO42nw9fMrQJdOb%2FARw19kR9JMAAMT0AJWXYCbdv%2B%2BFavhvqV6EL4PJ8FGpZw3g%3D%3D","locale":"en-US","buyingOptionType":"NEW"}]

$$39.99 () Includes selected options. Includes initial monthly payment and selected options. Details

Secure transaction

Ships from

Amazon.com

Sold by

Amazon.com

Details

Ships from

Amazon.com

Sold by

Amazon.com

Return policy: Eligible for Return, Refund or Replacement within 30 days of receipt

Add a gift receipt for easy returns

Have one to sell?

Sell on Amazon

Other Sellers on Amazon

Added

Not added

$45.21
& FREE Shipping

Sold by: Book Depository US

Added

Not added

$46.06
+ $3.99 shipping

Sold by: Prime Deals, USA

Flip to back Flip to front

Listen Playing... Paused You're listening to a sample of the Audible audio edition.
Learn more

See this image

Follow the Authors

Koki Saitoh

斎藤康毅

Deep Learning from the Basics: Python and Deep Learning: Theory and Implementation

by Koki Saitoh (Author)

20 ratings

See all formats and editions

Price

New from

Used from

Kindle

"Please retry"

$17.19

—

Paperback

"Please retry"

$39.99

$61.41

Kindle
$17.19 Read with Our Free App
Paperback
$39.99

2 Used from $61.41 9 New from $39.99

Enhance your purchase

Discover ways to implement various deep learning algorithms by leveraging Python and other technologies

Key Features

Learn deep learning models through several activities
Begin with simple machine learning problems, and finish by building a complex system of your own
Teach your machines to see by mastering the technologies required for image recognition

Book Description

Deep learning is rapidly becoming the most preferred way of solving data problems. This is thanks, in part, to its huge variety of mathematical algorithms and their ability to find patterns that are otherwise invisible to us.

Deep Learning from the Basics begins with a fast-paced introduction to deep learning with Python, its definition, characteristics, and applications. You'll learn how to use the Python interpreter and the script files in your applications, and utilize NumPy and Matplotlib in your deep learning models. As you progress through the book, you'll discover backpropagation―an efficient way to calculate the gradients of weight parameters―and study multilayer perceptrons and their limitations, before, finally, implementing a three-layer neural network and calculating multidimensional arrays.

By the end of the book, you'll have the knowledge to apply the relevant technologies in deep learning.

What you will learn

Use Python with minimum external sources to implement deep learning programs
Study the various deep learning and neural network theories
Learn how to determine learning coefficients and the initial values of weights
Implement trends such as Batch Normalization, Dropout, and Adam
Explore applications like automatic driving, image generation, and reinforcement learning

Who this book is for

Deep Learning from the Basics is designed for data scientists, data analysts, and developers who want to use deep learning techniques to develop efficient solutions. This book is ideal for those who want a deeper understanding as well as an overview of the technologies. Some working knowledge of Python is a must. Knowledge of NumPy and pandas will be beneficial, but not essential.

Frequently bought together

+

Total price:

To see our price, add these items to your cart.

Choose items to buy together.

by Koki Saitoh Paperback
$39.99
In Stock.
Ships from and sold by Amazon.com.
by James Loy Paperback
$40.35
In Stock.
Ships from and sold by Amazon.com.

Francois Chollet
221
Paperback
14 offers from $39.09
Sebastian Raschka
179
Paperback
18 offers from $46.79
Aurélien Géron
59
Paperback
35 offers from $52.50
Seth Weidman
86
Paperback
31 offers from $27.16
Steven D'Ascoli CPA
8
Paperback
2 offers from $29.69
Ian Goodfellow
1,950
Hardcover
in Hockey Coaching
39 offers from $64.24

Editorial Reviews

About the Author

Koki Saitoh was born in Tsushima, Nagasaki in 1984. He graduated from the engineering department of the Tokyo Institute of Technology and completed a master’s course at the Graduate School of Interdisciplinary Information Studies at the University of Tokyo. Currently, he conducts research and development in computer vision and machine learning. He has authored Python 3 in Practice, The Elements of Computing Systems, and Building Machine Learning Systems with Python, translations of which are published by O’Reilly, Japan.

Product details

Publisher ‏ : ‎ Packt Publishing (March 8, 2021)
Language ‏ : ‎ English
Paperback ‏ : ‎ 316 pages
ISBN-10 ‏ : ‎ 1800206135
ISBN-13 ‏ : ‎ 978-1800206137
Item Weight ‏ : ‎ 1.2 pounds
Dimensions ‏ : ‎ 7.5 x 0.72 x 9.25 inches

Best Sellers Rank: #531,156 in Books (See Top 100 in Books)
- #184 in Computer Neural Networks
- #651 in Python Programming
- #756 in Artificial Intelligence & Semantics

Customer Reviews:
20 ratings

Brief content visible, double tap to read full content.

Full content visible, double tap to read brief content.

Videos

Help others learn more about this product by uploading a video!

Upload your video

About the authors

Follow authors to get new release updates, plus improved recommendations.

Koki Saitoh
Brief content visible, double tap to read full content.
Full content visible, double tap to read brief content.
Discover more of the author’s books, see similar authors, read author blogs and more
See more on the author's page
斎藤康毅
Brief content visible, double tap to read full content.
Full content visible, double tap to read brief content.
Discover more of the author’s books, see similar authors, read author blogs and more
See more on the author's page

Customer reviews

4.3 out of 5

20 global ratings

5 star		62%
4 star		23%
3 star 0% (0%)		0%
2 star		16%
1 star 0% (0%)		0%

How customer reviews and ratings work

Top reviews from the United States

There was a problem filtering reviews right now. Please try again later.

Max J. Bamberger

Does a Good Job of Simplifying Extremely Complicated Concepts

Reviewed in the United States 🇺🇸 on July 28, 2021

The book manages to condense a lot of very technical and deep concepts into an easy-to-read manual that very navigable I feel I can pick back up any time I need a good refresher. It does read like a story which I love -- makes it feel more like a lecture rather than a textbook. All in all I'd say its similar to a "For Dummies" book, but without the distractions and fluffy side-notes. The book also features some good diagrams and figures which help tremendously.

The one criticism I have: It's took me a year and half to truly master Python when I was first introduced. I would consider it a necessary first step towards taking a technical dive into any Machine Learning, Artificial intelligence or Data Science topics. The book covers that in only 20 pages. From there, no time is spent on any Machine Learning concepts but instead goes right into Perceptrons which are fundamental building blocks for neural nets. I do wish there was some time spent in between to focus on more concepts in statistics, probability and ML algorithms like regression, ensemble models, boosting, the differences in types of ML use cases (unsupervised vs. supervised etc.).

All-in-all I would recommend it if you're a data analyst / scientist who knows some Python already and statistics already and feel you're ready to take on neural nets / deep learning.

Helpful

edkruegerdata

A Good Choice for Self-Study

Reviewed in the United States 🇺🇸 on April 8, 2021

"Deep Learning from the Basics: Python and Deep Learning" targets people with a bit of programming experience who are interested in understanding how deep learning works. It isn't a cookbook for ML/DL libraries. In fact, because its purpose is to teach how ML/DL works, its expositions only use Python, Numpy and Matplotlib.

One of the best ways to understand something is to make a simplified version yourself. Koki Saitoh guides you through this process with concise explanations that are straight to the point and reinforced with high-quality illustrations and implementations in python.

Unlike many basics texts, this one doesn't waste time teaching all the prerequisites from the beginning. The relevant prerequisites are covered just as you need them.

After a brief introduction to Python, Numpy and Matplotlib, the text jumps right into its subject matter, beginning with implementing logic gates, neural networks and training them. Backpropagation is explained exceptionally well, with a complete set of diagrams.

From this point, the text surveys some additional training techniques before covering CNNs. It ends with a survey of other techniques with links to implementations in the book's associated repo.

This book is, for the most part, an excellent choice for self-study and pedagogically well-conceived. However, the lack of exercises is a major impediment to its use for self-study. In a cookbook, it would make sense to leave them out. However, this is not a cookbook, and it wouldn't make sense to use this code in production settings -- you'd use the relevant libraries. Additionally, excessively detailed explanations of some of the simpler concepts and implementations can distract from the main line of argument.

Helpful

Eduardo Arias Reyes

Great introduction to the world of deep learning

Reviewed in the United States 🇺🇸 on April 20, 2021

If you are trying to understand deep learning, this book is a great starting point. The author starts by teaching basic concepts: Python, Numpy, and Matplotlib. Then he introduces more elaborate concepts such as the perceptron, neural networks, and their training process. Backpropagation is explained in detail. Finally, it presents deep neural network architectures with special emphasis on CNN.

Unlike many serious books that are hard to understand, it is really enjoyable to read this book because clearly explains how the components work together from the beginning to the end in concise and clear language.

This book does not describe how to use deep learning frameworks, such as TensorFlow, and PyTorch. It also does not refer to transformer-based architectures.

Helpful

Charles Tucker

A Functional Overview of How Deep Learning Works

Reviewed in the United States 🇺🇸 on April 15, 2021

I would recommend this book for any Data Scientists or aspiring Data Scientists who would like to better understand the inner workings (the how and why) of Deep Learning implementation.

This book is not a cookbook for designing a DL workflow using TensorFlow or PyTorch. It is a detailed explanation of the basics of DL as advertised, describing the math and theories behind how DL works. It accomplishes this using basic implementation of DL principles starting with perceptrons and building to Neural Networks and Deep Learning.

Visuals and scratch Python code using minimal packages or frameworks (primarily numpy) are used to illustrate the principles of DL using the MNIST dataset. Algorithms are designed from scratch with emphasis on the math behind them, and how they work. The focus is definitely on the basics and inner workings of DL.

I found Chapter 6 particularly interesting. Important topics are addressed here including discussing how choice of descent optimization algorithm can affect learning rate and how the distribution of activations in each layer affects training. The author reviews different weight initialization techniques, regularization, and briefly discusses hyperparameter tuning.

It helps to have a good understanding of math, particularly basic calculus such as derivatives in addition to vector/matrix math, but the author makes a good attempt to explain principles for someone with less knowledge in these areas. I think this book offers the opportunity for readers to better understand the math and theories behind DL, to help make better choices (or at least understand choices better) when implementing standard DL frameworks such as TensorFlow.

2 people found this helpful

Helpful

Tolga TUNCOGLU

Basics in Mathematical Terms

Reviewed in the United States 🇺🇸 on April 6, 2021

If you are looking to understand what is happening behind the scenes, if you are curious about mathematical explanations and want to get a clean yet base deep learning information this book is for you.

It covers the basics and the maths, it won’t give you guidance on how to use fancy libraries and apply DL in easy steps but it will make you understand so you can evaluate and explain better.

Helpful

Buy new:

$39.99

Other Sellers on Amazon

Follow the Authors

Deep Learning from the Basics: Python and Deep Learning: Theory and Implementation

Enhance your purchase

Key Features

Book Description

What you will learn

Who this book is for

Table of Contents

Frequently bought together

Customers who viewed this item also viewed

Editorial Reviews

About the Author

Product details

Videos

About the authors

Koki Saitoh

斎藤康毅

Customer reviews

Top reviews from the United States

There was a problem filtering reviews right now. Please try again later.

Buy new: $39.99

Other Sellers on Amazon

Follow the Authors

Deep Learning from the Basics: Python and Deep Learning: Theory and Implementation

Enhance your purchase

Key Features

Book Description

What you will learn

Who this book is for

Table of Contents

Frequently bought together

Customers who viewed this item also viewed

Editorial Reviews

About the Author

Product details

Videos

About the authors

Koki Saitoh

斎藤 康毅

Customer reviews

Top reviews from the United States

There was a problem filtering reviews right now. Please try again later.

Buy new:

$39.99

斎藤康毅