Serverless AI

A short presentation I used during an event in Istanbul where I talked about the use of Serverless in the AI space and what Azure services can be leveraged to implement Serverless AI solutions.

Transcript

1. Daron Yöndem http://daron.me @daronyondem
2. • Previously described as “(Mobile) Backend as a Service", BaaS • cloud-accessible databases (e.g., Parse, Firebase, CosmosDB), authentication services (e.g., Auth0, AWS Cognito) • Stateless compute containers that are event-triggered and fully managed by a third party; there comes “Functions as a Service” or "FaaS"
3. • Event-driven artificial intelligence (AI) • Real-Time AI • Scalability • Ease of deployment
7. Let’s talk tooling!
8. • Eventing • Machine Learning • Data Storage • Database • Compute
9. • Service Bus: Async Enterprise Messaging • Azure Event Hubs: Distributed Data Streaming • Relay: Secure two way communication without changes to your network • Event Grid: Cross cloud reactive eventing
10. • Cognitive Services • Azure Bot Service • Azure Machine Learning Service
11. • Azure Search : Cognitive Search, Built-in AI including OCR, key phrase extraction, and named entity recognition to unlock insights • Azure CosmosDB : NoSQL Document Type, Graph • Azure Tables : NoSQL key-value store • Azure Databricks: Apache SparkTM–based analytics service
12. • Azure Functions : Pyhton support! • Azure Container Instances
13. http://daron.me | @daronyondem Download slides here; http://daron.me/decks