Código QR (código de barras bidimensional)

U-TraCE: a conformal prediction approach to uncertainty quantification in black-box models

Modern machine learning (ML) systems, particularly deep neural networks, have become increasingly complex and opaque, making reliable uncertainty quantification (UQ) essential. Conventional UQ methods often prove inadequate for black-box model evaluation scenarios, either because model internals are...

תיאור מלא

שמור ב:
Principais autores: Edgardo J Marchi, Maik Liebl
פורמט: Artigo
שפה:Inglês
יצא לאור: IOP Publishing 2026-01-01
סדרה:Machine Learning: Science and Technology
נושאים:
uncertainty quantification
conformal prediction
U-TraCE
גישה מקוונת:https://doi.org/10.1088/2632-2153/ae35ce
תגים: הוספת תג
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!

פריטים דומים