How to architect a no-code ML platform on Google Cloud

Опубликовано 2 октября 2021, 16:00

Plainsight → goo.gle/3urQv0h
AI Simplified → goo.gle/AISimplified

Getting into data science and ML can be intimidating, no-code solutions make ML/AI approachable. But how are these no-code solutions made? In this episode of Architecting with Google Cloud, Priyanka Vergadia speaks with Carlos Anchia, CEO of Plainsight, a company that makes Vision AI accessible with no-code. Listen as they discuss the democratization of AI and how to use the Plainsight ML solution from Google Cloud Marketplace. You can have full control over your data, resources, and billing within your Google Cloud project!

Chapters:
0:00 - Intro
1:54 - How to create ML models using no-code Plainsight interface
4:25 - ML/AI Architecture deep dive
7:40 - How Plainsight uses Vertex AI to create custom containers to train the models
8:50 - Demo
10:05 - How to handle labeling with growing dataset
11:30 - Explainable AI
13:20 - Behind the scene look into no-code model training
16:14 - Using Pub/Sub messaging for served ML model so BI services and Apps can subscribe to the Pub/Sub topic
17:04 - Why Google Marketplace?
19:20 - Secret of success
20:40 - Summary

Architecting with Google Cloud playlist → goo.gle/3g7xAC9
Subscribe to Google Cloud Tech → goo.gle/GoogleCloudTech

#ArchitectingWithGoogleCloud

product: Cloud - General; fullname: Priyanka Vergadia; re_ty: Publish;