Тёмный

2.7. Deep dive into data drift detection. [OPTIONAL] 

Evidently AI
Подписаться 1 тыс.
Просмотров 592
50% 1

00:40 Drift detection methods
07:50 How to choose the approach to drift detection?
10:50 Drift detection for large datasets
12:55 Drift detection for non-batch models
14:30 Feature drift as a retraining trigger
16:30 How to interpret data and prediction drift together?
18:00 What to do when drift is detected?
In this video, we dive deep into different drift detection methods and how to choose the optimal approach for your dataset and problem statement. We cover special cases like handling large datasets, calculating drift for real-time models, and using drift as a retraining trigger. We also discuss how to interpret data and prediction drift and what to do if drift is detected.
RU-vid playlist: • Open-Source ML Observa...
Join the course: www.evidentlyai.com/ml-observ...
Course notes and info: learn.evidentlyai.com/
Discord community: / discord
Enjoyed the video? Star Evidently on GitHub: github.com/evidentlyai/evidently

Опубликовано:

 

13 окт 2023

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 1   
@greenjoy999
@greenjoy999 6 месяцев назад
These Content are Really Good
Далее
K - Nearest Neighbors (kNN)
26:25
Просмотров 11 тыс.
ML Drift: Identifying Issues Before You Have a Problem
15:25
Opensource, Uncensored, Unbothered. - Flux.1 Image Gen
18:59
Drifting Away: Testing ML Models in Production
55:08
Просмотров 16 тыс.