Humans Learn Using Manifolds, Reluctantly

Abstract

When the distribution of unlabeled data in feature space lies along a manifold, the information it provides may be used by a learner to assist classification in a semi-supervised setting. While manifold learning is well-known in machine learning, the use of manifolds in human learning is largely unstudied. We perform a set of experiments which test a human's ability to use a manifold in a semi-supervised learning task, under varying conditions. We show that humans may be encouraged into using the manifold, overcoming the strong preference for a simple, axis-parallel linear boundary.

Cite

Text

Rogers et al. "Humans Learn Using Manifolds, Reluctantly." Neural Information Processing Systems, 2010.

Markdown

[Rogers et al. "Humans Learn Using Manifolds, Reluctantly." Neural Information Processing Systems, 2010.](https://mlanthology.org/neurips/2010/rogers2010neurips-humans/)

BibTeX

@inproceedings{rogers2010neurips-humans,
  title     = {{Humans Learn Using Manifolds, Reluctantly}},
  author    = {Rogers, Tim and Kalish, Chuck and Harrison, Joseph and Zhu, Xiaojin and Gibson, Bryan R.},
  booktitle = {Neural Information Processing Systems},
  year      = {2010},
  pages     = {730-738},
  url       = {https://mlanthology.org/neurips/2010/rogers2010neurips-humans/}
}