Neural Networks

In Chapter 1, Machine Learning – an Introduction, we introduced a number of basic machine learning(ML) concepts and techniques. We went through the main ML paradigms, as well as some popular classic ML algorithms, and we finished with neural networks. In this chapter, we will formally introduce what neural networks are, describe in detail how a neuron works, see how we can stack many layers to create a deep feedforward neural network, and then we'll learn how to train them.

In this chapter, we will cover the following topics:

The need for neural networks
An introduction to neural networks
Training neural networks

Initially, neural networks were inspired by the biological brain (hence the name). Over time, however, we've stopped trying to emulate how the brain works and instead we focused on finding the correct configurations for specific tasks...

Filter reviews by

All

Amazon verified reviews

Steven Feb 19, 2019

This book provides a great introduction to deep and reinforcement learning. First, It does a good job at explaining in detail the basics of neural networks. Then, it gradually introduces more complex models like convolutional and recurrent networks in an easy to understand way.The computer vision section is comprehensive and has a good mix between theoretical and practical knowledge - especially the parts about residual networks, object detection, and generative networks.The chapter about natural language processing is good, but tries to introduce a lot of material in little space. It would have been better for the explanations to be more detailed, especially the attention models and speech recognition parts.It's interesting that the book also includes an introduction to reinforcement learning - it serves as a good basis for further research in this field.The chapter about autonomous vehicles deserves an honorable mention as well. It's rare to find this topic in other books.

Amazon Verified review

Georgi Petrov Feb 19, 2019

I do like the added history of AI and Machine learning, it makes it well clear what the differences are and how we often use the terms interchangeably. Even though it says "second edition" you don't need the first book. This book is also a good read for those who are not too deep into Deep Learning(pun intended), contains practical examples and the methodology is well explained. I am still new to the subject but the book was engaging with great practical examples which I was able to follow to the best of my skills. Highly recommend for any skill levels, it's a good motivation to boost up your technical skills.

Tobias Bockhorst Mar 26, 2020

Despite the fact that I've seen good publications by the authors previously,this particular one is somewhat improvable with respect to graphics quality,albeit some aspects here (e.g. contrast) may be somewhat related to PACKTpublishing as I've encountered rather poor graphics quality in some of theirtitles before.

Lily Apr 06, 2019

I like the topic selection, which covers virtually all major deep learning advancements in recent years starting from neural net basics and going all the way to reinforcement learning and autonomous vehicles. I also like that 3 of the major deep learning libraries are covered - it makes it easier for novices to compare them and understand their differences. A minor improvement would be to include jypiter notebooks in the code repository. I think this book can benefit beginners, because of the wide range of covered topics. It can also help more experienced people who want to improve your knowledge in some specific area (in my case GANs and reinforcement learning).

L Aug 07, 2020

As mentioned in the book, the book is for people with some basic understandings of machine learning. It's not a beginner book.The language is concise and easy to understand. The book provides a pretty comprehensive roadmap/summary to learn deep learnings and provides links for most of the landmark research papers.The printing quality can be further improved.The github repository link provided in the book points to the repo for a different book. You need to search for the first author's git repo for the python codes.

Python Deep Learning: Exploring deep learning techniques and neural network architectures with PyTorch, Keras, and TensorFlow , Second Edition

What do you get with Print?

Python Deep Learning

Neural Networks

The need for neural networks

An introduction to neural networks

Training neural networks

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 5 authors

FAQs

Python Deep Learning: Exploring deep learning techniques and neural network architectures with PyTorch, Keras, and TensorFlow , Second Edition

What do you get with Print?

Contact Details

Shipping Address

Billing Address

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with Print?

Contact Details

Shipping Address

Billing Address

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 5 authors

FAQs