Fundamentals of Data Science Solutions

Self-Learning Course

Take this course at your own pace through pre-recorded video and online resources.

Aimed at independent users, this course will guide you through the best metrics for assessing the performance of machine learning models. We’ll illustrate a range of use cases by looking at how we have applied machine learning to challenges spanning from healthcare to the reduction of industrial energy use. There will be some practical programming exercises to help you understand how to optimise your own models to increase performance. 

Learning objectives 

• Understanding the performance quality of a classifier/regressor model  
• Understanding the benefits and limitations of ensemble models and support vector machines  
• Utilisation of hyperparameter tuning to improve model performance  
• Develop skills to provide most suitable solution despite drawbacks to data and limitations  
• Ability to apply knowledge gained to an example data problem focussed on the industrial sector 

Pre-requisites

• This course will develop ideas from “Practical Guide to Machine Learning: Defining Problem Scope and Assessing Model Requirements“
• We recommend familiarity with programming in Python. 
• An understanding of basic statistical concepts (correlation, significance etc.) would also be useful. 

Create a free account to our Training Portal to register for a course and browse all available training courses.