Calibrating AI Models for Wireless Communications via Conformal Prediction

When used in complex engineered systems, such as communication networks, artificial intelligence (AI) models should be not only as accurate as possible, but also well calibrated. A well-calibrated AI model is one that can reliably quantify the uncertainty of its decisions, assigning high confidence...

وصف كامل

التفاصيل البيبلوغرافية

المؤلفون الرئيسيون:	Kfir M. Cohen, Sangwoo Park, Osvaldo Simeone, Shlomo Shamai Shitz
التنسيق:	Artigo
اللغة:	Inglês
منشور في:	IEEE 2023-01-01
سلاسل:	IEEE Transactions on Machine Learning in Communications and Networking
الموضوعات:	Bayesian learning calibration conformal prediction cross-validation reliability set prediction
الوصول للمادة أونلاين:	https://ieeexplore.ieee.org/document/10262367/
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!