Загрузка...
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...
Сохранить в:
| Опубликовано в: : | Adv Neural Inf Process Syst |
|---|---|
| Главные авторы: | , , , , |
| Формат: | Artigo |
| Язык: | Inglês |
| Опубликовано: |
2018
|
| Предметы: | |
| Online-ссылка: | https://ncbi.nlm.nih.gov/pmc/articles/PMC7899143/ https://ncbi.nlm.nih.gov/pubmed/33623354 |
| Метки: |
Добавить метку
Нет меток, Требуется 1-ая метка записи!
|