Industrial process transformation with Machine Learning using Kubeflow

Key Value
image https://assets.ubuntu.com/v1/ec5310fc-kubeflow+ai-h-white.svg
image_width 350
image_height 133
meta_image https://assets.ubuntu.com/v1/b0601692-facebook_and_linkedin_banner+(4).jpeg
meta_copydoc https://docs.google.com/document/d/1zNw6ghR0CzJQGdqWAX5QOaiK8tv-sImMqZ3h86NOzAA/edit?usp=sharing
banner_class k8s
webinar_code 458242
primary_cta Register for the webinar
primary_link #register-section

In this webinar, Canonical and Mavencode partner to explore the application of Machine Learning in an industrial processing plant where we try to determine the mean-time to failure, detect anomaly and recommend prescriptive maintenance for failure prevention and downtime reduction.

Mavencode will start by detailing how new tools like Kubeflow can be used to accelerate the time from model development to deployment in a real world scenario. Using anomaly detection and machinery failure prevention as a use-case, we will go over an architectural overview on how to get from data to actionable insight.

Finally, Canonical will discuss how you can tame the complexity of cloud-native projects such as Kubeflow through the concepts of charms, operators and application lifecycle management.