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

Building a Deep Feedforward Neural Network

In this chapter, we will cover the following recipes:

Training a vanilla neural network
Scaling the input dataset
Impact of training when the majority of inputs are greater than zero
Impact of batch size on model accuracy
Building a deep neural network to improve network accuracy
Varying the learning rate to improve network accuracy
Varying the loss optimizer to improve network accuracy
Understanding the scenario of overfitting
Speeding up the training process using batch normalization

In the previous chapter, we looked at the basics of the function of a neural network. We also learned that there are various hyperparameters that impact the accuracy of a neural network. In this chapter, we will get into the details of the functions of the various hyperparameters within a neural network.

All the codes for this chapter are available at...

Key benefits

From scratch, build multiple neural network architectures such as CNN, RNN, LSTM in Keras

Discover tips and tricks for designing a robust neural network to solve real-world problems

Graduate from understanding the working details of neural networks and master the art of fine-tuning them

Description

This book will take you from the basics of neural networks to advanced implementations of architectures using a recipe-based approach. We will learn about how neural networks work and the impact of various hyper parameters on a network's accuracy along with leveraging neural networks for structured and unstructured data. Later, we will learn how to classify and detect objects in images. We will also learn to use transfer learning for multiple applications, including a self-driving car using Convolutional Neural Networks. We will generate images while leveraging GANs and also by performing image encoding. Additionally, we will perform text analysis using word vector based techniques. Later, we will use Recurrent Neural Networks and LSTM to implement chatbot and Machine Translation systems. Finally, you will learn about transcribing images, audio, and generating captions and also use Deep Q-learning to build an agent that plays Space Invaders game. By the end of this book, you will have developed the skills to choose and customize multiple neural network architectures for various deep learning problems you might encounter.

Who is this book for?

This intermediate-level book targets beginners and intermediate-level machine learning practitioners and data scientists who have just started their journey with neural networks. This book is for those who are looking for resources to help them navigate through the various neural network architectures; you'll build multiple architectures, with concomitant case studies ordered by the complexity of the problem. A basic understanding of Python programming and a familiarity with basic machine learning are all you need to get started with this book.

What you will learn

Build multiple advanced neural network architectures from scratch

Explore transfer learning to perform object detection and classification

Build self-driving car applications using instance and semantic segmentation

Understand data encoding for image, text and recommender systems

Implement text analysis using sequence-to-sequence learning

Leverage a combination of CNN and RNN to perform end-to-end learning

Build agents to play games using deep Q-learning

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

€32.99

€32.99

€32.99

Total € 98.97

Filter reviews by

All

Amazon verified reviews

krishna Sep 23, 2019

The Word embedding concepts were clear, application oriented and neatly explained.The book is structured appropriate to the readers learning curve. The author is reachable on linkedin and is has an amazing intuitive way of explaining complicated NN architectures. This book is a must buy if you are into deep learning applications.

Amazon Verified review

drew lubz Oct 25, 2019

This book is perfect for practitioners in the intermediate stage of machine learning.. The different examples help understanding how to create real word applications....the organization of it ('how to do it' sections) are really good..

janga reddy Aug 31, 2019

I have gone through multiple books in vain, trying to understand the working details of various neural networks architectures. This book does an amazing job of detailing the steps involved in building neural network architectures step by step.The structure of book is easy for the reader to follow, with a logical flow from one chapter to another and from one use case to another.The code is easy to follow with commentary about each line of code. However, there are a couple of use cases where in the book, the imported libraries are to be upgraded to have the code working – sufficient information has been provided in the code’s github repository.The combination of detail in book and the corresponding github code for use cases ranging across the spectrum makes this a MUST-HAVE book for anyone beginning with neural networks.

JJG Jan 29, 2020

I love the content of this book, the best of many books I have purchased on the subject of machine learning. Want to give a 5, but there are many places where the formating just sucks. See my image for example.

Melanie L. Jan 04, 2020

It might be a valuable book if you're looking for Keras examples and references. But it is hard to read and lacking details. (Yes, this is a cookbook not a deep dive book after all.)

Scenario	Training dataset	Test dataset
5 epochs	97.59%	97.1%
100 epochs	100%	98.28%

Neural Networks with Keras Cookbook: Over 70 recipes leveraging deep learning techniques across image, text, audio, and game bots

What do you get with Print?

Neural Networks with Keras Cookbook

Building a Deep Feedforward Neural Network

Training a vanilla neural network

Getting ready

Scaling the input dataset

Getting ready

Impact on training when the majority of inputs are greater than zero

Getting ready

Impact of batch size on model accuracy

Getting ready

Building a deep neural network to improve network accuracy

Getting ready

Varying the learning rate to improve network accuracy

Getting ready

Varying the loss optimizer to improve network accuracy

Getting ready

Understanding the scenario of overfitting

Speeding up the training process using batch normalization

Page 1 of 10

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

Neural Networks with Keras Cookbook: Over 70 recipes leveraging deep learning techniques across image, text, audio, and game bots

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