What do you get with Print?

Instant access to your digital eBook copy whilst your Print order is Shipped

Paperback book shipped to your preferred address

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

The Nuts and Bolts of Neural Networks

In this chapter, we'll discuss some of the intricacies of neural networks (NNs)—the cornerstone of deep learning (DL). We'll talk about their mathematical apparatus, structure, and training. Our main goal is to provide you with a systematic understanding of NNs. Often, we approach them from a computer science perspective—as a machine learning (ML) algorithm (or even a special entity) composed of a number of different steps/components. We gain our intuition by thinking in terms of neurons, layers, and so on (at least I did this when I first learned about this field). This is a perfectly valid way to do things and we can still do impressive things at this level of understanding. Perhaps this is not the correct approach, though.

NNs have solid mathematical foundations and if we approach them from this point of view, we...

Key benefits

Get to grips with building faster and more robust deep learning architectures

Investigate and train convolutional neural network (CNN) models with GPU-accelerated libraries such as TensorFlow and PyTorch

Apply deep neural networks (DNNs) to computer vision problems, NLP, and GANs

Description

In order to build robust deep learning systems, you’ll need to understand everything from how neural networks work to training CNN models. In this book, you’ll discover newly developed deep learning models, methodologies used in the domain, and their implementation based on areas of application. You’ll start by understanding the building blocks and the math behind neural networks, and then move on to CNNs and their advanced applications in computer vision. You'll also learn to apply the most popular CNN architectures in object detection and image segmentation. Further on, you’ll focus on variational autoencoders and GANs. You’ll then use neural networks to extract sophisticated vector representations of words, before going on to cover various types of recurrent networks, such as LSTM and GRU. You’ll even explore the attention mechanism to process sequential data without the help of recurrent neural networks (RNNs). Later, you’ll use graph neural networks for processing structured data, along with covering meta-learning, which allows you to train neural networks with fewer training samples. Finally, you’ll understand how to apply deep learning to autonomous vehicles. By the end of this book, you’ll have mastered key deep learning concepts and the different applications of deep learning models in the real world.

Who is this book for?

This book is for data scientists, deep learning engineers and researchers, and AI developers who want to further their knowledge of deep learning and build innovative and unique deep learning projects. Anyone looking to get to grips with advanced use cases and methodologies adopted in the deep learning domain using real-world examples will also find this book useful. Basic understanding of deep learning concepts and working knowledge of the Python programming language is assumed.

What you will learn

Cover advanced and state-of-the-art neural network architectures

Understand the theory and math behind neural networks

Train DNNs and apply them to modern deep learning problems

Use CNNs for object detection and image segmentation

Implement generative adversarial networks (GANs) and variational autoencoders to generate new images

Solve natural language processing (NLP) tasks, such as machine translation, using sequence-to-sequence models

Understand DL techniques, such as meta-learning and graph neural networks

What do you get with Print?

Instant access to your digital eBook copy whilst your Print order is Shipped

Paperback book shipped to your preferred address

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Frequently bought together

Deep Learning with TensorFlow 2 and Keras

Can$55.99

Can$61.99

Can$69.99

Total Can$ 187.97 Stars icon

Filter reviews by

All

Amazon verified reviews

Kumar Bhargav Srinivasan Jan 18, 2021

Target audience for this book is : people who have basic knowledge of AI & Machine Learning.Topics which are perquisites:Basic Linear AlgebraStatisticsPython ( Not a hard requirement, but recommended)Pros:* If you are someone who doesn't remember, first chapter will make life easy for you. It has very thorough examples of each topic of Linear Algebra and statistics.* All the code implemented in the book are accessible via github which is very convenient to hands on on different datasets. I would recommend to run same code on different datasets to try it on your own.* "Put it together" is really nice way to revise all the topics learnt in the chapter.* All the chapters are mostly independent so if you want to focus on one topic than you can just read that chapter and grasp everything.* Personally, I really enjoyed section on text classification and BERT.Cons:* Code maybe hard for the ones who are not fluent in python but python is overall is easier to learn so I don't think this as a barrier to read this book.Overall, this book is really good read for the one who already have beginner level knowledge. I would definitely recommend for the fact it really dives into each topic to the advance level.

Amazon Verified review

Sunita Jan 14, 2021

The author of this book reached out to me and provided copy of the full book. I love the way author goes into details of each section in the book. You definitely need to have a prior knowledge of deep learning before diving into this book. The language of the book is fairly simple, clear and easy to understand. Knowing python is a must. I enjoyed reading the book thoroughly.

Amazon Customer Jan 14, 2021

What an amazing book! What an amazing Ivan Vasilev has undertaken!I've done several deep learning courses in the past. For those who prefer to know how actually deep learning works in-depth and how math is using behind the deep learning model prediction, this is a gold mine for them.I haven't finished all the materials in the book, but I've read a good way and while it's a different experience to doing the course online, I have been enjoying it so far. The book is well written, well-thought-out and it's started with basic math (concept) to the future of deep learning.I like language modeling and meta-learning most. I was very curious about some topics about how it works behind the scene. Because of this book, I got the most answers. Thank you, Ivan, to compile such a great book.Another great thing about this book is that the book code sample is readily available in GitHub so it's very convenient for me to explore furthermore without wasting time.After reading this book, I am amazed by the usage of math. Thank you Ivan for writing this book. I'll eagerly wait for the next release.

Steve Dec 31, 2020

I have generally reviewed this book, I found this is a very good book if you are a beginner or interested in the deep learning field with using python. This book can equip you with an overview of the necessary knowledge along with practical implementations in python, after reading this book, it expects that at least you could solve basic problems or even harder ones in your tasks and you would feel be comfortable to acquire new knowledge querying online in a fast way.Enjoy reading!

Chandra Dec 30, 2020

Disclaimer: The publisher reached out to me to review the book and provided me a copy of it.This book is for readers who already know about DL and want to know the latest in applying DL. This book covers a lot of breadth (vision, text, graphs, meta learning and autonomous vehicles) and depth in some topics (various vision and text neural network architectures). Book starts with an introduction to algebra, vector operations and calculus needed to understand DL concepts in chapter 1 and then ramps up to cover DL applications from chapter 2 onwards. I feel this book is good starting source for someone to get familiar with concepts of applying to DL to graphs and meta learning(there are abundant sources to learn about vision and text problems)If you are looking to learn from the basics, I recommend ‘deep learning’ Coursera course before buying this book.If you are looking to learn about PyTorch and Tensorflow frameworks (even though the title mentions them), I recommend you to look elsewhere.Final thoughts:Highly recommend for readers who are familiar with DL

Advanced Deep Learning with Python: Design and implement advanced next-generation AI solutions using TensorFlow and PyTorch

What do you get with Print?

Advanced Deep Learning with Python

The Nuts and Bolts of Neural Networks

The mathematical apparatus of NNs

Linear algebra

A short introduction to NNs

Neurons

Training NNs

Gradient descent

Summary

Page 1 of 5

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with Print?

Product Details

Frequently bought together

Table of Contents

Recommendations for you

Customer reviews

Filter reviews by

People who bought this also bought

About the author

FAQs

Advanced Deep Learning with Python: Design and implement advanced next-generation AI solutions using TensorFlow and PyTorch

What do you get with Print?

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with Print?

Product Details

Packt Subscriptions

Frequently bought together

Table of Contents

Recommendations for you

Customer reviews

Filter reviews by

People who bought this also bought

About the author

FAQs