From the course: Machine Learning and AI Foundations: Producing Explainable AI (XAI) and Interpretable Machine Learning Solutions
Join today to access over 24,900 courses taught by industry experts.
Why do we have black box models? - KNIME Tutorial
From the course: Machine Learning and AI Foundations: Producing Explainable AI (XAI) and Interpretable Machine Learning Solutions
Why do we have black box models?
- [Instructor] So if complex black box models have the potential to create challenges and extra work, there have to be some compelling reasons to do it. I'm going to list what I believe to be the most important reasons influencing the contemporary data science community. Each of these could be debated. And remember you always have choices. By the time the course concludes, you'll have a lot of information to weigh into your own decision to pursue either interpretable machine learning or black box with AI. Here are some of the main arguments I encounter in the data science community in favor of black box. The first reason that comes to mind, of course, is accuracy. The basic premise is that complex models are always more accurate. The full story is a bit more subtle, but this reason is so important that we'll dig a bit deeper on this one in the next video. I think we're also influenced by famous case studies natural language…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.