Introduction to experimental design for machine learning

Welcome to the course: Experimental design for machine learning

This course is designed to take one or two hours a week, for five weeks, to complete. It is aimed at bioscience professionals, particularly in the field of plant phenotyping, that are interested in the best way to design experiments to collect data for analysis using modern machine learning approaches.

Learning outcomes

The learning outcomes for the course, organised by week, are as follows:

• Design experiments that will collect good quality data for use in machine learning and deep learning models
• Improve and organise datasets collected experimentally for use in machine learning and deep learning models
• Compare and select machine learning and deep learning models for use with your experimental data
• Interpret and evaluate results from machine learning and deep learning models and discuss ethical considerations surrounding their use
• Report effectively on findings from machine learning and deep learning models trained on experimental data

The people behind the course

Your lead educators are: Andrew French, Michael Pound and Nathan Mellor.

We would also like to thank Sean Riley of Boardie Video Production for the video production itself.

In this video, Andy and Mike give an overview of the course content.

The course builds on another course in the DataCampp series, Machine learning for image data, which has a much deeper technical approach. The emphasis here, though, is on the wider thinking behind setting up a deep learning experiment for plant phenotyping, and give an overview of what is involved.

Development and delivery of this course is supported by a UKRI Large-scale data training grant MR/V038850/1, “Data CAMPP (Innovative Training in Data Capture, Analysis and Management for Plant Phenotyping)”