Wordt geladen...

Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices

In real-world machine learning applications, data subsets correspond to especially critical outcomes: vulnerable cyclist detections are safety-critical in an autonomous driving task, and “question” sentences might be important to a dialogue agent’s language understanding for product purposes. While...

Volledige beschrijving

Bewaard in:
Bibliografische gegevens
Gepubliceerd in:Adv Neural Inf Process Syst
Hoofdauteurs: Chen, Vincent S., Wu, Sen, Weng, Zhenzhen, Ratner, Alexander, Ré, Christopher
Formaat: Artigo
Taal:Inglês
Gepubliceerd in: 2019
Onderwerpen:
Online toegang:https://ncbi.nlm.nih.gov/pmc/articles/PMC6927210/
https://ncbi.nlm.nih.gov/pubmed/31871391
Tags: Voeg label toe
Geen labels, Wees de eerste die dit record labelt!