השוואת שיטות

	זיהוי מחוץ לתחום התפלגות	כיול מודל
תחום	למידת מכונה	למידת מכונה
משפחה	Machine learning	Machine learning
שנת המקור	2017	2017
הוגה השיטה	Hendrycks & Gimpel	Platt; Guo et al.
סוג	Reliability and safety method for neural networks	Post-hoc probability correction technique
מקור מכונן	Hendrycks, D., & Gimpel, K. (2017). A baseline for detecting misclassified and out-of-distribution examples in neural networks. International Conference on Learning Representations.	Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017). On calibration of modern neural networks. International Conference on Machine Learning, 1321–1330.
כינויים	OOD Detection, Novelty Detection, Open-Set Recognition, Dağılım Dışı Tespit	Classifier Calibration, Probability Calibration, Score Calibration, Model Kalibrasyonu
קשורות	3	3
תקציר	Out-of-Distribution (OOD) detection is a set of techniques that identify when a deployed machine learning model receives inputs that differ significantly from its training data distribution. Introduced as a formal problem by Hendrycks and Gimpel in 2017, these methods enable models to flag unfamiliar inputs rather than silently produce unreliable predictions, making them foundational to trustworthy and safe AI deployment in high-stakes domains.	Model calibration is a post-hoc technique that adjusts the probability outputs of a trained classifier so that predicted confidence scores match empirical outcome frequencies. A classifier is said to be perfectly calibrated if, among all predictions made with confidence p, exactly a fraction p of them are correct. Systematic miscalibration of modern deep neural networks was rigorously documented by Guo et al. (2017), who showed that networks trained with standard cross-entropy loss tend to be overconfident, and proposed temperature scaling as a simple, effective remedy.