Exploring Java Machine Learning Environments
There are an increasing number of tools for Machine Learning in Java. This course will teach you how to choose the appropriate tool for your machine learning task, as well as how to get started with the tool and how to use it.
What you'll learn
Choosing the right tool for a machine learning problem among the myriad options is not easy. In this course, Exploring Java Machine Learning Environments, you’ll learn to assess, identify, and use the right tool for the job. First, you’ll explore several characteristics of the available tools for machine learning in Java. Next, you’ll discover the pros and cons of each tool depending on multiple scenarios. Finally, you’ll learn how to get started with each of the tools, consuming data, training a model, evaluating and visualizing the performance in different environments and at different scales. When you’re finished with this course, you’ll have the skills and knowledge of the Machine Learning Java Environment needed to effectively implement industry-grade pipelines.
Table of contents
- Introduction 4m
- Demo: Data Preparation and Loading with Programmatic Weka 3m
- Demo: Data Preprocessing with Programmatic Weka 2m
- Demo: Implementing K-means with Programmatic Weka 1m
- Demo: Evaluation and Visualization with Programmatic Weka 5m
- Demo: The Full Workflow in One Go with Weka GUI 4m
- Summary 1m
- Introduction 5m
- Demo: Data Preparation and Loading with DL4J (Part 1: Setup) 4m
- Demo: Data Preparation and Loading with DL4J (Part 2: DL4J DataSetIterator) 7m
- Demo: Data Preprocessing with DL4J 9m
- Demo: Implementing a Twitter Sentiment Classifier with DL4J 5m
- Demo: Performance and Evaluation and Visualization with DL4J 2m
- Summary 1m