Exponential Moving Average Statistics Tracking For Inference

via “exponential-moving-average-statistics-tracking-for-inference”

* 🏆 2015: [Going Deeper With Convolutions (Inception)](https://www.cv-foundation.org/openaccess/content_cvpr_2015/html/Szegedy_Going_Deeper_With_2015_CVPR_paper.html)

Unique: Decouples training dynamics (where batch statistics are informative) from inference dynamics (where population statistics are necessary) via exponential moving average accumulation — this two-phase approach became the standard pattern for all batch-dependent normalization techniques and influenced subsequent work on test-time adaptation