The Seen and Unseen Factors Influencing Machine Perception of Images and Language

The Seen and Unseen Factors Influencing Machine Perception of Images and Language: The success of machine learning has recently surged, with similar algorithmic approaches effectively solving a variety of human-defined tasks. Tasks testing how well machines can perceive images and communicate about them have begun to show a lot of promise, and at the same time, have exposed strong effects of different types of bias, such as overgeneralization. In this talk, I will detail how machines are learning about the visual world, and discuss how machine learning and different kinds of bias interact.

View the slides for this session