Member-only story

Causal Reasoning in Machine Learning

An investigation through some of the main limitations Artificial Intelligence-powered systems are facing

Pier Paolo Ippolito
Towards Data Science
6 min readJul 15, 2021

--

Photo by Dan Meyers on Unsplash

Introduction

Thanks to recent advancements in Artificial Intelligence (AI), we are now able to leverage Machine Learning and Deep Learning technologies in both academic and commercial applications. Although, relying just on correlations between the different features, can possibly lead to wrong conclusions since correlation does not necessarily imply causation. Two of the main limitations of nowadays Machine Learning and Deep Learning models are:

  • Robustness: trained models might not be able to generalise to new data and therefore would not be able to provide robust and reliable performances in the real world.
  • Explainability: complex Deep Learning models can be difficult to analyse in order to clearly demonstrate their decision-making process.

Developing models able to identify cause-effect relationships between different variables might ultimately offer a solution to solve both of these problems. This idea has also been supported by researchers such as Judea Pearl, which advocated how having models able to reason in uncertainties could not be enough to enable researchers to create machines able to…

--

--

Towards Data Science
Towards Data Science

Published in Towards Data Science

Your home for data science and AI. The world’s leading publication for data science, data analytics, data engineering, machine learning, and artificial intelligence professionals.

Pier Paolo Ippolito
Pier Paolo Ippolito

Responses (1)