Načítá se...

Human-in-the-Loop Interpretability Prior

We often desire our models to be interpretable as well as accurate. Prior work on optimizing models for interpretability has relied on easy-to-quantify proxies for interpretability, such as sparsity or the number of operations required. In this work, we optimize for interpretability by directly incl...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Adv Neural Inf Process Syst
Hlavní autoři: Lage, Isaac, Ross, Andrew Slavin, Kim, Been, Gershman, Samuel J., Doshi-Velez, Finale
Médium: Artigo
Jazyk:Inglês
Vydáno: 2018
Témata:
On-line přístup:https://ncbi.nlm.nih.gov/pmc/articles/PMC7899143/
https://ncbi.nlm.nih.gov/pubmed/33623354
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!