There is a growing need for investigating how machine learning models operate. With this work, we aim to understand trained machine learning models by questioning their data preferences. We propose a mathematical framework that allows us to probe trained models and identify their preferred samples in various scenarios including prediction-risky, parameter-sensitive, or model-contrastive samples. To showcase our framework, we pose these queries to a range of models trained on a range of classification and regression tasks, and receive answers in the form of generated data.

Unless you've been on a media blackout, chances are you've seen some news story or new startup boasting about new developments in artificial intelligence (AI) and machine learning (ML). My own company is one of those startups. But beyond leveraging AI in our logo generator, we also have a dedicated data science team continually researching new applications and developments in AI and ML. As we look for what these technologies can do for our business, we continue to come across the same question: Are all methods of ML equally effective? A lot of people are used to hearing the terms AI and ML said in the same breath, but there are a few important distinctions between the two.