Python Deep learning: Develop your first Neural Network in Python Using TensorFlow, Keras, and PyTorch (Step-by-Step Tutorial for Beginners)
Product ID: 121352147
Build your Own Neural Network through easy-to-follow instruction and examples. Thanks this easy tutorial you’ll learn the fundamentals of Deep learning and build your very own Neural Network in Python using TensorFlow, Keras, PyTorch, and Theano. While you have the option of spending thousands of dollars on a big and à boring textbooks, we recommend getting the same pieces of information for a fraction of the cost. So Get Your Copy Now!! Why this book? Book Objectives The following are the objectives of this book: To help you understand deep learning in detail To help you know how to get started with deep learning in Python by setting up the coding environment. To help you transition from a deep learning Beginner to a Professional. To help you learn how to develop a complete and functional artificial neural network model in Python on your own. Who this Book is for? The author targets the following groups of people: Anybody who is a complete beginner to deep learning with Python. Anybody in need of advancing their Python for deep learning skills. Professors, lecturers or tutors who are looking to find better ways to explain Deep Learning to their students in the simplest and easiest way. Students and academicians, especially those focusing on python programming, neural networks, machine learning, and deep learning. What do you need for this Book? You are required to have installed the following on your computer: Python 3.X. TensorFlow . Keras . PyTorch The Author guides you on how to install the rest of the Python libraries that are required for deep learning. The author will guide you on how to install and configure the rest. What is inside the book? What is Deep Learning? An Overview of Artificial Neural Networks. Exploring the Libraries. Installation and Setup. TensorFlow Basics. Deep Learning with TensorFlow. Keras Basics. PyTorch Basics. Creating Convolutional Neural Networks with PyTorch. Creating Recurrent Neural Networks with PyTorch. From the back cover. Deep learning is part of machine learning methods based on learning data representations. This book written by Samuel Burns provides an excellent introduction to deep learning methods for computer vision applications. The author does not focus on too much math since this guide is designed for developers who are beginners in the field of deep learning. The book has been grouped into chapters, with each chapter exploring a different feature of the deep learning libraries that can be used in Python programming language. Each chapter features a unique Neural Network architecture including Convolutional Neural Networks. After reading this book, you will be able to build your own Neural Networks using Tenserflow, Keras, and PyTorch. Moreover, the author has provided Python codes, each code performing a different task. Corresponding explanations have also been provided alongside each piece of code to help the reader understand the meaning of the various lines of the code. In addition to this, screenshots showing the output that each code should return have been given. The author has used a simple language to make it easy even for beginners to understand. Review: Straight into the code without a Higher-Level understanding of what's going on. + Many typos. - Note: I only made it through Chapter 6. I gave up because I considered this to be useless resource. The book gives a high-level overview of what the code is doing, but leaves out any explanation of the lower-level functionality of the code. For example, page 49 covers creating a model, but doesn't mention why we are to do that and what the model is. It doesn't discuss the library/class being used. Normally this is fine, but coupled with the lack of understanding of why we're doing this step leaves the reader (or maybe just me) in the dark of what's going on. No overview of Neural Networks. Chapter 2 is "An Overview of Artificial Neural Networks", but it's literally 2 pages. So i gave up in Chapter 6 because I felt that despite being a book for beginners, it wasn't really teaching me much about Deep Learning, but rather just regurgitating someone else's code. But even then, you have to fix the code sometimes. Example: Page 43 adds 2 extra lines of code that cause errors and seemingly don't need to be there. The same block of code also imports Numpy, despite not being used. Review: A starting point - The book starts out alright with documented examples, but then stops explaining what the code is doing. You will have an entire page of code that isn't documented leaving you to have to look up the instruction and attempt to figure out what is going on. The author should put more of an explanation of the code on the web somewhere as the various websites for the libraries used like TensorFlow, have code with explanations.
| Best Sellers Rank | #2,662,507 in Kindle Store ( See Top 100 in Kindle Store ) #1,103 in Neural Networks #1,739 in Computer Neural Networks #5,039 in AI & Semantics |
M**R
Straight into the code without a Higher-Level understanding of what's going on. + Many typos.
Note: I only made it through Chapter 6. I gave up because I considered this to be useless resource. The book gives a high-level overview of what the code is doing, but leaves out any explanation of the lower-level functionality of the code. For example, page 49 covers creating a model, but doesn't mention why we are to do that and what the model is. It doesn't discuss the library/class being used. Normally this is fine, but coupled with the lack of understanding of why we're doing this step leaves the reader (or maybe just me) in the dark of what's going on. No overview of Neural Networks. Chapter 2 is "An Overview of Artificial Neural Networks", but it's literally 2 pages. So i gave up in Chapter 6 because I felt that despite being a book for beginners, it wasn't really teaching me much about Deep Learning, but rather just regurgitating someone else's code. But even then, you have to fix the code sometimes. Example: Page 43 adds 2 extra lines of code that cause errors and seemingly don't need to be there. The same block of code also imports Numpy, despite not being used.
J**.
A starting point
The book starts out alright with documented examples, but then stops explaining what the code is doing. You will have an entire page of code that isn't documented leaving you to have to look up the instruction and attempt to figure out what is going on. The author should put more of an explanation of the code on the web somewhere as the various websites for the libraries used like TensorFlow, have code with explanations.
B**O
deep learning practices
dislike its long text in coding.
A**N
no big deal
THe big picture is ok but nothing goes deep
K**A
very limited examples
The book had very few examples and it doesn't really go past an MNIST example. The book has one chapter on RNNs but doesn't cover anything else. It's poorly explained and documented.
J**N
Deep learning
A good introduction to neural networks that is more beginner-friendly than most. You dont need a good understanding of calculus or Algebra.
K**D
Not bad.
This is the best introductory book on Deep learning and neural networks .if you want to learn about neural networks and how to make them in code, this is the best tutorial to start.
A**C
Correcto
Excelente producto, lo he aprovechado mucho.
M**D
Limited Education
Although the code examples are useful, I was disappointed in the quality of education in this book. There is very little in the way of explanation about why we're writing these lines of code. It's a useful resource as long as your expectations are clear.
L**N
Navrant
Ce livre est une honte : pas un schéma, les explications sont à côté de la plaque et on trouve bien mieux en tuto sur le net. Par ailleurs copier des pages entières de log d'apprentissage est la preuve que l'auteur n'a rien d'intéressant à raconter.
Trustpilot
2 weeks ago
2 days ago