Rethinking human-in-the-loop for artificial augmented intelligence

Figure 1: In real-world applications, we think there exists a human-machine loop where humans and machines are mutually augmenting each other. We call it Artificial Augmented Intelligence. How do we build and evaluate an AI system for real-world applications? In most AI research, the evaluation of AI methods involves a training-validation-testing process. The experiments usually stop when the models have good testing performance on the reported datasets because real-world data distribution is assumed to be modeled by the validation and testing data.