Advanced Machine Learning Using SAS® Viya®

Advanced machine learning modelers who use Model Studio

• Develop a series of supervised learning models based on techniques such as logistic regression, decision tree, neural network, and support vector machine
• Evaluate classifier performance of your model
• Create an ensemble model based on different techniques
• Preprocess and engineer features from categorical and continuous data to improve the performance of your machine learning models
• Extract features using principal component analysis, singular value decomposition, robust principal component analysis, autoencoders, and variable clustering
• Discover the basic concepts of cluster analysis, and then study a set of typical clustering methodologies, algorithms, and applications
• Use statistics and machine learning to detect anomalies in your data
• Implement a semi-supervised learning model
• vImport and run SAS 9 models in Model Studio
• Run open-source models in Model Studio
• Automate different stages of machine learning in SAS Viya
• Generate automated pipelines using REST API

Before attending this course, it is recommended that you have done the following:

• Completed the Machine Learning Using SAS Viya course.
• Obtained some experience with creating and managing SAS data sets, which you can gain from the SAS(R) Programming I: Essentials course.
• Acquired some experience building statistical models using SAS Visual Data Mining and Machine Learning software.

Machine Learning Fundamentals

• Model Studio review
• Classifier performance
• Ensemble learning

Feature Engineering

• Introduction to feature engineering
• Principal component analysis
• Singular value decomposition
• Robust principal component analysis
• Autoencoders
• Transforming categorical variables

Clustering of Variables and Observations

• Variable clustering
• Cluster analysis

Anomaly Detection

• Introduction to anomaly detection
• Support vector data description
• Semi-supervised learning

External Models in Model Studio

• Importing SAS Enterprise Miner models
• Running SAS/STAT or SAS Enterprise Miner models
• Running open-source models

Machine Learning Automation

• Automation in SAS Viya
• Data preprocessing and feature engineering
• Modeling
• Automated pipeline creation
• Pipeline automation using REST API (self-study)

Tips and Tricks with Model Studio

• Managing metadata
• Working with analysis elements
• Using the SAS Code node
• Interpreting models with extracted features
• Scoring unsupervised learning models