Construct · 1 fields · 1 citations

concept activation vector: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Explainable artificial intelligence

a direction in a network's internal activations representing a human-defined concept, used to test how strongly that concept drives a prediction.

In explainable artificial intelligence, concept activation vector refers to a direction in a network's internal activations representing a human-defined concept, used to test how strongly that concept drives a prediction. This meaning comes from Kim (2017) in arXiv.[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how concept activation vector sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

activation4 fields · 4 citationsjingle · one word, four constructs explainable artificial intelligence1 fields · 1 citationsanchor · a standalone construct intelligence6 fields · 14 citationsjingle · one name, six constructs

References

Kim, B., Wattenberg, M., Gilmer, J., Cai, C., Wexler, J., Viegas, F., & Sayres, R. (2017). Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV). arXiv. https://doi.org/10.48550/arxiv.1711.11279

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct