Study Guide

Objective

You can manage and pre-process sequential data, such as time-series data
You can apply common sequential data machine learning tools while creating machine learning models
You can create suitable error metrics for your sequential data machine learning models
You can create classification and forecasting machine learning models with sequential data
You can use a created sequential data machine learning model in conventional programming environments as a feature
You can share your results and exercises via a version control system.

Content

Sequential data vs independent and identically distributed data (IID)
Data analytics and machine learning solutions for sequential data
Sequential data pre-processing
Challenges and limitations regarding sequential data and machine learning
Common classic machine learning tools for sequential data

Qualifications

Basics of programming, Basics of common Python data analytics modules/libraries, Basics of conventional machine learning methods

Assessment criteria, satisfactory (1)

You can apply basic tools for sequential data based machine learning models
You can do basic data pre-processing required for training a sequential data-based machine learning models
You can use conventional error metrics while training a sequential data –based machine learning model
You can connect a trained model into a conventional programming environment
You can share your results and exercises via a version control system.

Assessment criteria, good (3)

You can apply common tools for sequential data based machine learning models
You can do necessary data pre-processing required for training a sequential data-based machine learning models
You can use conventional error metrics while training a sequential data –based machine learning model
You can connect a trained model into a conventional programming environment
You can perform algorithm optimization based on data and algorithm used
You can share your results and exercises via a version control system.

Assessment criteria, excellent (5)

You can apply common tools for sequential data based machine learning models
You can do advanced data pre-processing required for training a sequential data-based machine learning models
You can use conventional error metrics while training a sequential data –based machine learning model
You can connect a trained model into a conventional programming environment
You can perform algorithm optimization based on data and algorithm used
You can apply advanced machine learning algorithms and tools while creating sequential data-based machine learning models
You can share your results and exercises via a version control system.