Exploiting and Guiding User Interaction in Interactive Machine Teaching

TL;DR

This paper explores Interactive Machine Teaching (IMT), aiming to improve human-AI teaching interactions by exploiting and guiding user input, which enhances both AI model performance and user experience.

Contribution

It introduces IMT systems that effectively exploit and guide user interactions, advancing the design of human-centered AI teaching methods.

Findings

Enhanced AI model learning efficiency

Improved user teaching experience

Effective integration of human interaction in AI training

Abstract

Humans are talented with the ability to perform diverse interactions in the teaching process. However, when humans want to teach AI, existing interactive systems only allow humans to perform repetitive labeling, causing an unsatisfactory teaching experience. My Ph.D. research studies Interactive Machine Teaching (IMT), an emerging field of HCI research that aims to enhance humans' teaching experience in the AI creation process. My research builds IMT systems that exploit and guide user interaction and shows that such in-depth integration of human interaction can benefit both AI models and user experience.