▶Book Description
As the amount of data in the world continues to grow at an almost incomprehensible rate, being able to understand and process data is becoming a key differentiator for competitive organizations. Machine learning applications are everywhere, from self-driving cars, spam detection, document search, and trading strategies, to speech recognition. This makes machine learning well-suited to the present-day era of big data and Data Science. The main challenge is how to transform data into actionable knowledge.
Machine Learning in Java will provide you with the techniques and tools you need. You will start by learning how to apply machine learning methods to a variety of common tasks including classification, prediction, forecasting, market basket analysis, and clustering. The code in this book works for JDK 8 and above, the code is tested on JDK 11.
Moving on, you will discover how to detect anomalies and fraud, and ways to perform activity recognition, image recognition, and text analysis. By the end of the book, you will have explored related web resources and technologies that will help you take your learning to the next level.
By applying the most effective machine learning methods to real-world problems, you will gain hands-on experience that will transform the way you think about data.
▶What You Will Learn
⦁ Discover key Java machine learning libraries
⦁ Implement concepts such as classification, regression, and clustering
⦁ Develop a customer retention strategy by predicting likely churn candidates
⦁ Build a scalable recommendation engine with Apache Mahout
⦁ Apply machine learning to fraud, anomaly, and outlier detection
⦁ Experiment with deep learning concepts and algorithms
⦁ Write your own activity recognition model for eHealth applications
▶Key Features
⦁ Solve predictive modeling problems using the most popular machine learning Java libraries
⦁ Explore data processing, machine learning, and NLP concepts using JavaML, WEKA, MALLET libraries
⦁ Practical examples, tips, and tricks to help you understand applied machine learning in Java
▶Who This Book Is For
If you want to learn how to use Java's machine learning libraries to gain insight from your data, this book is for you. It will get you up and running quickly and provide you with the skills you need to successfully create, customize, and deploy machine learning applications with ease. You should be familiar with Java programming and some basic data mining concepts to make the most of this book, but no prior experience with machine learning is required.
▶What this book covers
⦁ Chapter 1, Applied Machine Learning Quick Start, introduces the field of natural language processing (NLP). The tools and basic techniques that support NLP are discussed. The use of models, their validation, and their use from a conceptual perspective are presented.
⦁ Chapter 2, Java Libraries and Platforms for Machine Learning, covers the purpose and uses of tokenizers. Different tokenization processes will be explored, followed by how they can be used to solve specific problems.
⦁ Chapter 3, Basic Algorithms – Classification, Regression, and Clustering, covers the problems associated with sentence detection. Correct detection of the end of sentences is important for many reasons. We will examine different approaches to this problem using a variety of examples.
⦁ Chapter 4, Customer Relationship Prediction with Ensembles, covers the process and problems associated with name recognition. Finding names, locations, and various things in a document is an important step in NLP. The techniques available are identified and demonstrated.
⦁ Chapter 5, Affinity Analysis, covers the process of determining the part of speech that is useful in determining the importance of words and their relationships in a document. It is a process that can enhance the effectiveness of other NLP tasks.
⦁ Chapter 6, Recommendation Engine with Apache Mahout, covers traditional features that do not apply to text documents. In this chapter, we'll learn how text documents can be presented.
⦁ Chapter 7, Fraud and Anomaly Detection, covers information retrieval, which entails finding documents in an unstructured format, such as text that satisfies a query.
⦁ Chapter 8, Image Recognition with Deeplearning4J, covers the issues surrounding how documents and text can be classified. Once we have isolated the parts of text, we can begin the process of analyzing it for information. One of these processes involves classifying and clustering information.
⦁ Chapter 9, Activity Recognition with Mobile Phone Sensors, demonstrates how to discover topics in a set of documents.
⦁ Chapter 10, Text Mining with Mallet – Topic Modeling and Spam Detection, covers the use of parsers and chunkers to solve text problems that are then examined. This important process, which normally results in a parse tree, provides insights into the structure and meaning of documents.
⦁ Chapter 11, What is Next?, brings together many of the topics in previous chapters to address other more sophisticated problems. The use and construction of a pipeline is discussed. The use of open source tools to support these operations is presented.
