Introducing Azure Anomaly Detector
Play Bring Anomaly Detector on-premises with containers support
Description
In the last episode of the AI Show we took a look at an amazing new service: the Azure Anomaly Detector. While these services are great, sometimes keeping everything local is a must given industry regulations, dealing with network latency, or you just want to have everything in-house. In this episode Qun Ying returns to describe how to bring this amazing service on premises using containers.
- Join Anomaly Detector Containers preview
- Check out the overview of the API service
- Create your first Anomaly Detector resource on Azure
- Find the Azure Notebook demo (remember to uncheck "Public" when you clone your instances)
- Join "Anomaly Detector Advisors" public community to connect with the product team and other members in the community
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
Download
More episodes in this series
Anomaly Detector v1.0 Best Practices
Related episodes
Anomaly detection on streaming data using Azure Databricks
Anomaly Detector v1.0 Best Practices
Introducing Azure Anomaly Detector
Machine Learning Interpretability Toolkit
Knowledge Mining with Azure Search
Machine Learning Models
Azure AI: Bringing artificial intelligence to every developer
Knowledge mining using the knowledge store feature of Azure Search
ONNX Runtime speeds up Image Embedding model in Bing Semantic Precise Image Search
Machine Learning with ML.NET 1.0 from Build 2019
The Discussion
-
Chris Too quick to hit Enter!. It's "on-premises", not "on-premise"
-
sethjuarez @Chris: Great catch!!! Thanks for that - I've made the correction. -
RipinA Hi,
Great demo. I respect the concept of billing which requires internet connectivity. But, there could be on-premises (edge) scenarios where internet connectivity can not be guaranteed always.
What will happen during such a scenario, will
1. Anomaly Detector keeps detecting the anomalies and once the internet connection is reestablished upload the billing telemetry to Azure
OR
2. Stop detecting as soon as the internet disconnects. Once the internet connection is reestablished, start with real-time data.
Regards,
Ripin Aggarwal