An interactive tool lets users reshape a model's latent space during training via a human-teacher loss term, with a 14-person user study reporting modest accuracy improvements.
Controlling machine-learning algorithms and their biases.McKin- sey Insights, 2017
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Human in the Latent Loop (HILL): Interactively Guiding Model Training Through Human Intuition
An interactive tool lets users reshape a model's latent space during training via a human-teacher loss term, with a 14-person user study reporting modest accuracy improvements.