From the course: Machine Learning and AI Foundations: Producing Explainable AI (XAI) and Interpretable Machine Learning Solutions

Unlock the full course today

Join today to access over 24,900 courses taught by industry experts.

Rashomon effect

Rashomon effect - KNIME Tutorial

From the course: Machine Learning and AI Foundations: Producing Explainable AI (XAI) and Interpretable Machine Learning Solutions

Start my 1-month free trial Buy for my team

Rashomon effect

“

- [Instructor] So you've built your model and you're listing your input variables in order of importance. You're excited to share this information with the team. And then you wonder, you almost went with a different model. You tried lots of different models. And the one that was second in terms of accuracy was nearly as good a performer. What if you had gone with the other model? Would this list of the most important variables be similar or perhaps rather different? The name Rashmon comes originally from a famous mid-century Japanese movie by Akira Kurosawa. In the film, four different witnesses describe a murder, but with differing and often contradictory details. It's become a metaphor for different points of view. The use of Rashmon as a metaphor in machine learning comes from a very influential paper by Leo Breiman. "The Two Cultures". Leo Breiman was a brilliant innovator that along with others brought us…

Contents