What do you get with a Packt Subscription?

Free for first 7 days. $19.99 p/m after that. Cancel any time!

Unlimited ad-free access to the largest independent learning library in tech. Access this title and thousands more!

50+ new titles added per month, including many first-to-market concepts and exclusive early access to books as they are being written.

Innovative learning tools, including AI book assistants, code context explainers, and text-to-speech.

Thousands of reference materials covering every tech concept you need to stay up to date.

Subscribe now

View plans & pricing

Using Deep Learning to Solve Regression Problems

In this chapter, we will build a simple multilayer perceptron (MLP), which is a fancy name for a neural network with a single hidden layer, to solve a regression problem. Then we will go deeper with a deep neural network that has several hidden layers. Along the way, we will explore model performance and over fitting. So, let's get started!

We will cover the following topics in this chapter:

Regression analysis and deep neural networks
Using deep neural networks for regression
Building an MLP in Keras
Building a deep neural network in Keras
Saving and loading a trained Keras model

Key benefits

A quick reference to all important deep learning concepts and their implementations

Essential tips, tricks, and hacks to train a variety of deep learning models such as CNNs, RNNs, LSTMs, and more

Supplemented with essential mathematics and theory, every chapter provides best practices and safe choices for training and fine-tuning your models in Keras and Tensorflow.

Description

Deep learning has become an essential necessity to enter the world of artificial intelligence. With this book deep learning techniques will become more accessible, practical, and relevant to practicing data scientists. It moves deep learning from academia to the real world through practical examples. You will learn how Tensor Board is used to monitor the training of deep neural networks and solve binary classification problems using deep learning. Readers will then learn to optimize hyperparameters in their deep learning models. The book then takes the readers through the practical implementation of training CNN's, RNN's, and LSTM's with word embeddings and seq2seq models from scratch. Later the book explores advanced topics such as Deep Q Network to solve an autonomous agent problem and how to use two adversarial networks to generate artificial images that appear real. For implementation purposes, we look at popular Python-based deep learning frameworks such as Keras and Tensorflow, Each chapter provides best practices and safe choices to help readers make the right decision while training deep neural networks. By the end of this book, you will be able to solve real-world problems quickly with deep neural networks.

Who is this book for?

If you are a Data Scientist or a Machine Learning expert, then this book is a very useful read in training your advanced machine learning and deep learning models. You can also refer this book if you are stuck in-between the neural network modeling and need immediate assistance in getting accomplishing the task smoothly. Some prior knowledge of Python and tight hold on the basics of machine learning is required.

What you will learn

Solve regression and classification challenges with TensorFlow and Keras

Learn to use Tensor Board for monitoring neural networks and its training

Optimize hyperparameters and safe choices/best practices

Build CNN s, RNN s, and LSTM s and using word embedding from scratch

Build and train seq2seq models for machine translation and chat applications.

Understanding Deep Q networks and how to use one to solve an autonomous agent problem.

Explore Deep Q Network and address autonomous agent challenges.

What do you get with a Packt Subscription?

Free for first 7 days. $19.99 p/m after that. Cancel any time!

Unlimited ad-free access to the largest independent learning library in tech. Access this title and thousands more!

50+ new titles added per month, including many first-to-market concepts and exclusive early access to books as they are being written.

Innovative learning tools, including AI book assistants, code context explainers, and text-to-speech.

Thousands of reference materials covering every tech concept you need to stay up to date.

Subscribe now

View plans & pricing

Frequently bought together

$43.99

TensorFlow: Powerful Predictive Analytics with TensorFlow

$43.99

$43.99

Total $ 131.97

Filter reviews by

All

Amazon verified reviews

Sara May 21, 2018

I found this book to be one of the more comprehensive but still easily 'readable' texts on practical application of deep learning techniques. The project and code examples are practical, and display a variety of useful deep learning techniques. This will be a book I will likely reference again and again for tips and reminders as I work on deep learning projects both at work and in hobby coding.While there are a lot of exciting ideas and usecases presented in the book, the one I found most useful was one of the more 'humble' ideas, at least mathematically speaking... I really appreciated the deep dive into TensorBoard, and showing some really useful things to do with that particular tool. It showed some things that aren't always necessarily obvious to do from the documentation. The information presented will help make TensorBoard a much more prominent tool in my deep learning development process than it has been so far.

Amazon Verified review

Ms. One More Time Aug 06, 2018

Love all the code in the book. Almost every bit of it worked without bugs. Almost every book of this type I have read had weak code that was often broken. This book was ten stars in this area.The level of text details was just perfect for me. I am past the beginner stage but not by much. I now feel after reading and running I can venture into kaggle datasets using Keras.I really loved learning about Tensorboard. It really helps me see if my model is too stupid or a real over fitter.

Shannon Apr 20, 2018

This book has really accelerated my education in deep learning with a wide range of case studies that helped me understand how and when to use different deep learning solutions. It comes with a great git repo with the code for each chapter, so I could follow the code along with the text. I’ve taken deep learning MOOCs where I implemented neural networks in numpy and spent a lot of time on the math and theory, but this book has a variety of practical examples that make this topic a lot more accessible.A nice constant in this book is that it stays at a high level, but provides great references along the way if I want to take a deeper dive into a topic later on. This helped me stay focused to start implementing code, rather than diving into complex theories and sending me into endless Wikipedia loops.The author has a really approachable voice; he explains things clearly with humor and without condescension. I am particularly excited to use this book’s example on LSTMs to build a predictive model on cryptocurrency pricing to make better trading decisions!

muuh Mar 16, 2019

I am interested in applying machine learning and deep learning in practice, not so much in learning the details of the math and writing all the algorithms from scratch myself. I have taken various online courses from Coursera, Udemy, etc. Those tend to go either into the math at a level I am not interested in, or scratch the surface with very basic examples.This book provides foundations to understand what the different types of models (LSTM, CNN, MLP) are based on, and illustrates each with various realistic case studies and models, along with explanations. For me this provided a great way to get the overall idea, build and understanding, and apply the models to my data and problems. Sometimes I did go looking for a bit more in-depth understanding on how each model works, but the explanations in this book are the ones that enabled me to do that.Also having all the code available (and working) on Github is great for quick reference. Just have to remember to look for "deep learning reference github", and can quickly find myself a reminder on how to write some specific code.

Winston Li Apr 20, 2018

I have an ebook version of this book, which I very much enjoyed reading. First of all, I really appreciate the author’s effort in nicely and properly formatting the equations and code snippets so that they are reader-friendly on kindle e-readers. It’s usually difficult to find a math/programming related ebook formatted well.As an analytics professional, I like the breadth of the book which covers almost all important types of deep learning frameworks and the usecases of each one. It does not focus only on Deep Learning, but also gives great overviews of more general backgrounds, such as time series for recurrent neural networks and NLP for LSTM/seq2seq models. The reader will have a full picture of the fields without losing the main concentration on Deep Learning. At the same time, the book keeps the depth of the content at the right amount so that the reader can quickly grasp the concept but also have sufficient math to get started with implementation and see how things play out. In addition, the book goes gradually from simple but foundational blocks to advanced models, which I find very easy to digest despite of the complexity of most the advanced topics.This book is a great starting point for people who are familiar with programming and some basic machine learning concepts, but want to know more about deep learning, especially what the state of the art looks like. It is also a good reference book for professionals who are familiar with the concepts but want to double check on how Deep Learning frameworks are set up in Tensorflow or Keras. The book comes with a lot of code examples, and also complete data and tutorial code downloadable through github. I personally like the fact that the book also covers how to locally set up GPU for deep learning, which is such an important topic yet a lot of deep learning books easily skip.

Deep Learning Quick Reference: Useful hacks for training and optimizing deep neural networks with TensorFlow and Keras

What do you get with a Packt Subscription?

Deep Learning Quick Reference

Using Deep Learning to Solve Regression Problems

Regression analysis and deep neural networks

Using deep neural networks for regression

How to plan a machine learning problem

Building an MLP in Keras

Input layer shape

Building a deep neural network in Keras

Saving and loading a trained Keras model

Summary

Page 1 of 7

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with a Packt Subscription?

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

Deep Learning Quick Reference: Useful hacks for training and optimizing deep neural networks with TensorFlow and Keras

What do you get with a Packt Subscription?

Key benefits

Description

Who is this book for?

What you will learn

Product Details

What do you get with a Packt Subscription?

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