Introduction

Artificial Intelligence (AI) and Machine Learning (ML) have become a ubiquitous part of modern technology, as they help deliver insights otherwise hidden in data for improved decision making and possibly automated responses or actions. By combining AI/ML with IoT, you can now leverage the large amounts of data generated by connected devices for learning based on real-world data and apply those learnings in use cases ranging from image and speech recognition to predictive maintenance and anomaly detection. 

With Cumulocity we provide a product and tooling to support you along every step of the Machine Learning lifecycle:

  1. Connect machines, ingest the raw machine data, perform data preparation to ensure AI-ready data and make it accessible for AI/ML model training in your data science tool of choice.
  2. Focus on the operational aspects of the Machine Learning lifecycle which involves applying a trained model to the incoming IoT data to obtain predictions, scoring, or insights in the cloud and/or at the edge.
  3. Seamlessly deploy and orchestrate AI/ML models not only in cloud or (thick) edge, but also at the device edge for an entire fleet of assets.

AI/ML model

The next sections will explain how you can realize an end-to-end Machine Learning solution leveraging the Cumulocity platform and integrated Data Science & Machine Learning (DSML) components, tooling, as well as platforms. These could be open source components such as TensorFlow and/or tooling from some of our leading AI/ML partners such as Microsoft Azure, AWS (Amazon Web Services), IBM or Boon Logic.