Master Class—Scaling Artificial Intelligence (AI): From Model Development to Operationalization

Drifting data poses three problems: detecting and assessing drift-related model performance degradation; generating a more accurate model from the new data; and deploying a new model into an existing machine-learning pipeline. See a solution that addresses each of these challenges through an example of a real-world predictive maintenance problem. We reduce the complexity and costs of operating the system—as well as increase its reliability—by automating both drift detection and data labeling. Learn how to develop streaming analytics on a desktop, deploy those solutions to the cloud, and apply AutoML strategies to keep your models up-to-date and their predictions as accurate as possible.

Highlights:

• Developing an end-to-end MLOps pipeline
• Monitoring an AI model from drifting data/ behaviour
• Generating automatic training datafrom incoming data<
• Retraining and redeploying models
• Use case: Battery SOC estimation