This section lists various open-source
software packages available from the Evolutionary AI
team. These are available for research purposes only; for
commercial use, contact
Unless otherwise specified, the packages are provided "as-is",
i.e. as concrete implementations of technologies described in
our research papers.
The Traveling Observer Model (TOM) implements deep multi-task learning through spatial variable embeddings.
In this competition, predictors were developed to forecast number of cases and prescriptors to recommend non-pharmaceutical interventions to cope with the COVID-19 pandemic. The package includes sample predictors and prescriptors and their evaluation code (see the competition tech page for details).
Residual-based error detection (RED) extends RIO to classification. It detects misclassification errors and distinguishes them from out-of-distribution inputs and adversarial inputs.
Residual estimation with an input/output kernel (RIO) quantifies confidence in point-prediction models and improves their accuracy.
Modular Universal Reparameterization (MUiR) makes deep multitask learning possible across diverse domains such as language, vision, genetics, etc.
A model management framework to help simplify and expedite model building. This package is maintained.