Program Summary
The Artificial Intelligence Research Associate (AIRA) program is part of a broad DARPA initiative to develop and apply “Third Wave” AI technologies that are robust to sparse data and adversarial spoofing, and that incorporate domain-relevant knowledge through generative contextual and explanatory models.
The vision of the AIRA program is to elevate AI to the role of an insightful and trusted collaborator in the scientific process. A key challenge today is the lack of generalizability of statistical AI methodologies beyond the narrow set of questions they are initially trained on and their poor ability to interpret beyond training. Overcoming the challenges outlined above will require new ideas to generate “deep insights” based on physics-, math-, and context-aware learned representations that succinctly capture relevant dynamics and behaviors of the complex systems under study and can generalize across domains.
To facilitate use of AI in the scientific process, AIRA will challenge the research community to address two main objectives: 1) explore and develop new AI architectures and approaches to facilitate the discovery of physical laws and models governing complex physical phenomena; 2) explore new approaches to assess where data are too sparse, noisy, or are otherwise inadequate to build predictive models; to generate testable hypotheses; to identify high-value experiments that could alleviate the problems of data shortfalls; and to quantify the confidence of predictions outside of the training space.