Exploring Machine Teaching with Children

TL;DR

This study investigates how children interact with machine teaching interfaces, revealing design principles that enhance their understanding and engagement with machine learning concepts through hands-on activities.

Contribution

It provides empirical insights into children's reasoning about ML and offers design guidelines for creating effective machine teaching experiences for young learners.

Findings

Children benefit from visible ML metrics during experimentation.

Exchanging models promotes reflection and pattern recognition.

Interfaces should support quick data inspection for better understanding.

Abstract

Iteratively building and testing machine learning models can help children develop creativity, flexibility, and comfort with machine learning and artificial intelligence. We explore how children use machine teaching interfaces with a team of 14 children (aged 7-13 years) and adult co-designers. Children trained image classifiers and tested each other's models for robustness. Our study illuminates how children reason about ML concepts, offering these insights for designing machine teaching experiences for children: (i) ML metrics (e.g. confidence scores) should be visible for experimentation; (ii) ML activities should enable children to exchange models for promoting reflection and pattern recognition; and (iii) the interface should allow quick data inspection (e.g. images vs. gestures).