Core ML

Core ML represents a horizontal effort within our Machine Learning (ML) group to create libraries that are reusable across our solutions, to open source code and data, and to establish internal best practices for ML code and model development.

Current projects under the purview of core ML include the development of: 

  1. A generic, extensible codebase to handle tabular data tasks, with algorithmic support ranging from classical ML models to deep neural nets
  2. A generic object detection library 

These codebases benefit from, and support further work in, a number of our solutions projects, including Pest Management, TB Adherence, and Pregnancy Risk Stratification. It is expected that their applicability to solutions projects will only increase going forward.