Why Do Some Machine Learning Models Fail?

What you'll learn

Most Machine Learning (ML) talks present beautiful cases of success, but, in reality, ML models often fail to deliver the desired performance. It is not uncommon to see developers blaming certain ML models and even providing blacklists of ML models. In this talk, Rafael Garcia-Dias will provide some tips on choosing ML models and guide them through the path of finding a good solution. Rafael will also present two of his recent works that use machine learning in astrophysics and in neuroscience.

Table of contents