Can You Define Model-Based Machine Learning?
This article is an introduction to Model Based Machine Learning by Tom Diethe, a research fellow on the SPHERE project at the University of Bristol and co-author of a soon to be published book on Model Based Machine Learning.
Instead of trying to find the right algorithm that will fit the problem, Model Based Machine Learning builds the model around the problem by formalizing in mathematical form all the available assumptions about the data such as the number and nature of the variables and their interactions.
In certain scenarios when there is a need to go beyond the black box approach of common machine learning models or when these models do not perform well enough, Model-Based Machine Learning provides another angle of attack.
Learn more about this topic and others just like it our Data Science Conferences, training sessions and workshops.
Did you find this article useful?
Help others find it by commenting and sharing.