Trusting Machine Learning Models with LIME

Machine learning models are often criticized for being black boxes. If a human cannot determine why the model arrives at the decision it made, there's good cause for skepticism. Classic inspection approaches to model interpretability are only useful for simple models, which are likely to only cover simple problems.

Guest

Marco Tulio Ribeiro: I'm a researcher at Google DeepMind. I am also an Affiliate Assistant Professor at the University of Washington, where I was previously a Ph.D student advised by Carlos Guestrin and Sameer Singh. My research is mostly on helping humans interact with machine learning models meaningfully. That involves interpretability, trust, debugging, feedback, etc.