Harnessing AI for Development and Evaluation of Systems (HADES)
MTSI supports the Federal Government by leveraging our MTSI-developed HADES Tool that verifies real world performance and improves the robustness and reliability of Machine Learning/AI-based algorithms.
Customer:
Applied Solutions:
The HADES ‘Adversary’ algorithm learns the performance space of a potential classification algorithm that could be fielded. The Adversary maps performance bounds by making changes to the physical domain which creates features that stimulate the classification algorithm and learning the relationship between this physical domain and the classifier outputs. This creates new data sets which can be used to improve the classifier and make it more robust in real-world situations.
