Book Image

Mastering Java for Data Science

By : Alexey Grigorev
Book Image

Mastering Java for Data Science

By: Alexey Grigorev

Overview of this book

Java is the most popular programming language, according to the TIOBE index, and it is a typical choice for running production systems in many companies, both in the startup world and among large enterprises. Not surprisingly, it is also a common choice for creating data science applications: it is fast and has a great set of data processing tools, both built-in and external. What is more, choosing Java for data science allows you to easily integrate solutions with existing software, and bring data science into production with less effort. This book will teach you how to create data science applications with Java. First, we will revise the most important things when starting a data science application, and then brush up the basics of Java and machine learning before diving into more advanced topics. We start by going over the existing libraries for data processing and libraries with machine learning algorithms. After that, we cover topics such as classification and regression, dimensionality reduction and clustering, information retrieval and natural language processing, and deep learning and big data. Finally, we finish the book by talking about the ways to deploy the model and evaluate it in production settings.
Table of Contents (17 chapters)
Title Page
About the Author
About the Reviewers
Customer Feedback

Chapter 8. Deep Learning with DeepLearning4J

In the previous chapter, we covered Extreme Gradient Boosting (XGBoost)--a library that implements the gradient boosting machine algorithm. This library provides state-of-the-art performance for many supervised machine learning problems. However, XGBoost only shines when the data is already structured and there are good handmade features.

The feature engineering process is usually quite complex and requires a lot of effort, especially when it comes to unstructured information such as images, sounds, or videos. This is the area where deep learning algorithms are usually superior to others, including XGBoost; they do not need hand-crafted features and are able to learn the structure of the data themselves.

In this chapter, we will look into a deep learning library for Java--DeepLearning4J. This library allows us to easily specify complex neural network architectures that are able to process unstructured data such as images. In particular, we will...