Implementing Machine Learning Workflow with RapidMiner
In this course, you will learn how you can develop your machine learning workflow using RapidMiner Studio, a data science platform for data preparation, machine learning, and predictive model deployment.
What you'll learn
RapidMiner Studio provides an integrated development environment for data visualization, data preparation, machine learning, and deployment. In this course, Implementing Machine Learning Workflow with RapidMiner, you will get an overview of how you can use drag-n-drop operators to build and train machine learning models.
First, you will get introduced to RapidMiner studio, which is a no-code technology to develop your machine learning workflow. You will perform exploratory data analysis using RapidMiner, build linear regression models, evaluate models using cross-validation, and perform feature selection and normalization of input data, without writing a single line of code.
Next, you will explore a native Java library for traditional machine learning models. The Java Statistical Analysis Tool, or JSAT library, is a pure Java library that allows you to train regression, classification, and clustering models. You will use JSAT to perform linear regression, perform classification using logistic regression and decision trees, perform clustering using k-means clustering, and deploy your model using the SpringBoot framework in a limited production environment.
Finally, you will see how you can use the Deep Java Library, or DJL, to train neural network models in Java. DJL provides a native Java API and can run your training on multiple backends such as Apache MXNet, TensorFlow, and PyTorch. You will also leverage transfer learning and use pre-trained models for image classification, image segmentation, and natural language processing.
When you are finished with this course, you will be able to use no-code technologies and native Java libraries to build and train machine learning models.
Table of contents
- Version Check 0m
- Prerequisites and Course Outline 3m
- Introducing RapidMiner 3m
- Demo: Download and Setup RapidMiner 4m
- Demo: Setting up a Repository and Importing Data 4m
- Demo: Exploring the Dataset 7m
- Demo: Build and Evaluate a Linear Regression Model 5m
- Demo: Train Model on Training Data and Evaluate Using Test Data 4m
- Demo: Perform Attribute Selection 4m
- Demo: Evaluate a Model Using Cross-validation 5m
- Demo: Assign Roles and Perform Attribute Selection 5m
- Demo: Train a Model with Normalized Data 6m
- Introducing JSAT 3m
- Demo: Getting Set up with a Maven Project 4m
- Demo: Loading and Exploring Data 5m
- Demo: Building and Training a Regression Model 5m
- Demo: Evaluating a Regression Model 3m
- Demo: Training and Evaluating a Ridge Regression Model 4m
- Demo: Building and Evaluating a Logistic Regression Classification Model 6m
- Demo: Building and Evaluating a Decision Tree Classification Model 2m
- Demo: Performing Clustering and Evaluating Clustering Models 6m
- Demo: Serializing and Deserializing Trained Models 4m
- Demo: Making Predictions Using a Deployed Model 6m
- Introducing DJL 3m
- Brief Overview of Neural Networks 3m
- Demo: Setting up the Maven Project and Dependencies 2m
- Demo: Building a Fully Connected Neural Network for Image Classification 6m
- Demo: Training the Image Classification Model 3m
- Demo: Performing Predictions Using the Classification Model 6m
- Brief Overview of Transfer Learning 3m
- Demo: Using a Pretrained Model for Image Classification 4m
- Demo: Using a Pretrained Model for Image Segmentation 5m
- Introducing Google BERT 2m
- Demo: Answering Questions with Google BERT 4m
- Summary and Further Study 2m