# Learning Concept Embeddings with Combined Human-Machine Expertise

arXiv: https://arxiv.org/abs/1509.07479 · HTML: https://mlsanity.com/paper/1509.07479/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2015.

## Built on by (most cited first, 6 of 6)

- [Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval](https://mlsanity.com/paper/2302.01332/) (2023)
- [Learning to Taste: A Multimodal Wine Dataset](https://mlsanity.com/paper/2308.16900/) (2023)
- [Searching for Structure in Unfalsifiable Claims](https://mlsanity.com/paper/2209.00495/) (2022)
- [Transductive Conformal Inference for Full Ranking](https://mlsanity.com/paper/2501.11384/) (2025)
- [PENCIL: Deep Learning with Noisy Labels](https://mlsanity.com/paper/2202.08436/) (2022)
- [Distribution-informed Efficient Conformal Prediction for Full Ranking](https://mlsanity.com/paper/2601.23128/) (2026)

## Abstract (arXiv)

This paper presents our work on "SNaCK," a low-dimensional concept embedding algorithm that combines human expertise with automatic machine similarity kernels. Both parts are complimentary: human insight can capture relationships that are not apparent from the object's visual similarity and the machine can help relieve the human from having to exhaustively specify many constraints. We show that our SNaCK embeddings are useful in several tasks: distinguishing prime and nonprime numbers on MNIST, discovering labeling mistakes in the Caltech UCSD Birds (CUB) dataset with the help of deep-learned features, creating training datasets for bird classifiers, capturing subjective human taste on a new dataset of 10,000 foods, and qualitatively exploring an unstructured set of pictographic characters. Comparisons with the state-of-the-art in these tasks show that SNaCK produces better concept embeddings that require less human supervision than the leading methods.