In our last two episodes we learned a bit about the Azure Anomaly Detector service. We first learned a bit about what it is and how it can be used. Then we looked into bringing the service on premises using containers. As with any service of this kind sometimes it takes a little tweaking to get things to the next level. In this episode Qun Ying gives three amazing tips that will help when we design our monitoring application architecture.
- Check out the cool demo on this episode
- Find the detailed documentation on the best practices
- Check out the overview of the API service
- Create your first Anomaly Detector resource on Azure
- Join Anomaly Detector Containers preview
- Join "Anomaly Detector Advisors" public community to connect with the product team and other members in the community
- [00:46] Tip 1: Batch mode versus streaming mode in Anomaly Detector.
- [02:76] Tip 2: How to detect anomalies from streaming time series data with Anomaly Detector?
- [05:00] An interactive demo of streaming anomaly detection.
- [06:36] Python code of streaming anomaly detection with Anomaly Detector APIs.
- [07:39] Tip 3: How to pre-process data for Anomaly Detector APIs?
- [08:00] What if the input time series is not evenly distributed?
- [09:04] How to improve the accuracy if the data has seasonal patterns?
The AI Show's Favorite Links:
- Don't miss new episodes, subscribe to the AI Show
- Create a Free account (Azure)
- Follow Seth on Twitter
- AI Blog
- Fast ML
- MIT News | AI
- Medium | Francesca Lazzeri
- Deep Learning vs. Machine Learning
- Follow Channel 9 On Twitter