Defense Advanced Research Projects AgencyTagged Content List


A process or rule set used for calculations or other problem-solving operations

Showing 108 results for Algorithms RSS
In order to transform machine learning systems from tools into partners, users need to trust their machine counterpart. One component to building a trusted relationship is knowledge of a partner’s competence (an accurate insight into a partner’s skills, experience, and reliability in dynamic environments). While state-of-the-art machine learning systems can perform well when their behaviors are applied in contexts similar to their learning experiences, they are unable to communicate their task strategies, the completeness of their training relative to a given task, the factors that may influence their actions, or their likelihood to succeed under specific conditions.
Accurate multi-physics simulation codes are essential for understanding the behavior of complex DoD systems, but they are generally not available from the commercial sector and have to be custom built. Current approaches to building simulation codes scale poorly with the number of interacting physics involved and often introduce inaccuracies that are difficult to trace and quantify.
CREATE aims to explore the utility of artificial intelligence (AI) on the autonomous formation of scalable machine-to-machine teams capable of reacting to and learning from unexpected missions in the absence of centralized communication and control. CREATE seeks to develop the theoretical foundations of autonomous AI teaming to enable a system of heterogeneous, contextually-aware agents to act in a decentralized manner and satisfy multiple, simultaneous and unplanned missions goals.
Deep Purple aims to advance the modeling of complex dynamic systems using new information-efficient approaches that make optimal use of data and known physics at multiple scales. The program is investigating next-generation deep learning approaches that use not only high throughput multimodal scientific data from observations and controlled experiments (including behaviors such as phase transitions and chaos), but also of the known science of such systems at whatever scales it exists.
Conventional analog-to-digital converters (ADCs) are fundamentally limited by timing jitter in the sampling source, forcing a trade-off between bandwidth and resolution. As a result, radio frequency (RF) systems are typically designed with narrow-bandwidth channels. These engineering constraints present problems when faced with broadband signals and ultra-short pulses. At high carrier frequencies, RF systems are further limited by the tuner that must mix down to baseband for electronic digitization.