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 24,700 courses taught by industry experts.

Comparing IML and XAI

Comparing IML and XAI - 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

Comparing IML and XAI

“

- [Instructor] We've mentioned that there are two distinct worldviews and approaches to providing transparency in our model's predictions. Let's start by discussing the explainable AI approach in more detail. Black box techniques, like deep learning and XG boost, are increasingly popular. They dominate the list of winning entries on machine learning competitions, like those on Kaggle, but their very nature makes them difficult to explain or interpret. For example, in medical AI, there are models that can accurately indicate the presence of disease, but it is often unclear, even to a doctor, how the model was able to make that determination. Yet, there are situations, including medical AI, where we need to be able to explain not only what the predictions are, but why that particular prediction was made. This is also true of the loans and reason codes that we discussed in the previous video. So the motivation for XAI is…

Contents