Book Image

Java Deep Learning Cookbook

By : Rahul Raj

Book Image

Java Deep Learning Cookbook

By: Rahul Raj

Overview of this book

Java is one of the most widely used programming languages in the world. With this book, you will see how to perform deep learning using Deeplearning4j (DL4J) – the most popular Java library for training neural networks efficiently. This book starts by showing you how to install and configure Java and DL4J on your system. You will then gain insights into deep learning basics and use your knowledge to create a deep neural network for binary classification from scratch. As you progress, you will discover how to build a convolutional neural network (CNN) in DL4J, and understand how to construct numeric vectors from text. This deep learning book will also guide you through performing anomaly detection on unsupervised data and help you set up neural networks in distributed systems effectively. In addition to this, you will learn how to import models from Keras and change the configuration in a pre-trained DL4J model. Finally, you will explore benchmarking in DL4J and optimize neural networks for optimal results. By the end of this book, you will have a clear understanding of how you can use DL4J to build robust deep learning applications in Java.

Preface

Who this book is for

What this book covers

To get the most out of this book

Free Chapter

Introduction to Deep Learning in Java

Introduction to Deep Learning in Java

Technical requirements

Deep learning intuition

Determining the right network type to solve deep learning problems

Determining the right activation function

Combating overfitting problems

Determining the right batch size and learning rates

Configuring Maven for DL4J

Configuring DL4J for a GPU-accelerated environment

Troubleshooting installation issues

Data Extraction, Transformation, and Loading

Data Extraction, Transformation, and Loading

Technical requirements

Reading and iterating through data

Performing schema transformations

Building a transformation process

Serializing transforms

Executing a transform process

Normalizing data for network efficiency

Building Deep Neural Networks for Binary Classification

Building Deep Neural Networks for Binary Classification

Technical requirements

Extracting data from CSV input

Removing anomalies from the data

Applying transformations to the data

Designing input layers for the neural network model

Designing hidden layers for the neural network model

Designing output layers for the neural network model

Training and evaluating the neural network model for CSV data

Deploying the neural network model and using it as an API

Building Convolutional Neural Networks

Building Convolutional Neural Networks

Technical requirements

Extracting images from disk

Creating image variations for training data

Image preprocessing and the design of input layers

Constructing hidden layers for a CNN

Constructing output layers for output classification

Training images and evaluating CNN output

Creating an API endpoint for the image classifier

Implementing Natural Language Processing

Implementing Natural Language Processing

Technical requirements

Reading and loading text data

Tokenizing data and training the model

Evaluating the model

Generating plots from the model

Saving and reloading the model

Importing Google News vectors

Troubleshooting and tuning Word2Vec models

Using Word2Vec for sentence classification using CNNs

Using Doc2Vec for document classification

Constructing an LSTM Network for Time Series

Constructing an LSTM Network for Time Series

Technical requirements

Extracting and reading clinical data

Loading and transforming data

Constructing input layers for the network

Constructing output layers for the network

Training time series data

Evaluating the LSTM network's efficiency

Constructing an LSTM Neural Network for Sequence Classification

Constructing an LSTM Neural Network for Sequence Classification

Technical requirements

Extracting time series data

Loading training data

Normalizing training data

Constructing input layers for the network

Constructing output layers for the network

Evaluating the LSTM network for classified output

Performing Anomaly Detection on Unsupervised Data

Performing Anomaly Detection on Unsupervised Data

Technical requirements

Extracting and preparing MNIST data

Constructing dense layers for input

Constructing output layers

Training with MNIST images

Evaluating and sorting the results based on the anomaly score

Saving the resultant model

Using RL4J for Reinforcement Learning

Using RL4J for Reinforcement Learning

Technical requirements

Setting up the Malmo environment and respective dependencies

Setting up the data requirements

Configuring and training a DQN agent

Evaluating a Malmo agent

Developing Applications in a Distributed Environment

Developing Applications in a Distributed Environment

Technical requirements

Setting up DL4J and the required dependencies

Creating an uber-JAR for training

CPU/GPU-specific configuration for training

Memory settings and garbage collection for Spark

Configuring encoding thresholds

Performing a distributed test set evaluation

Saving and loading trained neural network models

Performing distributed inference

Applying Transfer Learning to Network Models

Applying Transfer Learning to Network Models

Technical requirements

Modifying an existing customer retention model

Fine-tuning the learning configurations

Implementing frozen layers

Importing and loading Keras models and layers

Benchmarking and Neural Network Optimization

Benchmarking and Neural Network Optimization

Technical requirements

DL4J/ND4J-specific configuration

Setting up heap spaces and garbage collection

Using asynchronous ETL

Using arbiter to monitor neural network behavior

Performing hyperparameter tuning

Other Books You May Enjoy

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Constructing an LSTM Network for Time Series

In this chapter, we will discuss how to construct a long short-term memory (LSTM) neural network to solve a medical time series problem. We will be using data from 4,000 intensive care unit (ICU) patients. Our goal is to predict the mortality of patients using a given set of generic and sequential features. We have six generic features, such as age, gender, and weight. Also, we have 37 sequential features, such as cholesterol level, temperature, pH, and glucose level. Each patient has multiple measurements recorded against these sequential features. The number of measurements taken from each patient differs. Furthermore, the time between measurements also differs among patients.

LSTM is well-suited to this type of problem due to the sequential nature of the data. We could also solve it using a regular recurrent neural network (RNN)...