Dense, dynamic RF environments produce high-throughput data that is difficult to interpret, store, and transmit quickly enough for mission-critical decisions.
Infleqtion introduced Contextual Machine Learning on NVIDIA CUDA-Q and advanced its QuIRC platform through a $1 million U.S. Navy Phase II contract.
Operational systems need to preserve the information required for accurate RF analysis while reducing computational, storage, and transmission demands at the edge.
QuIRC is a self-learning preprocessing platform that uses CML to capture contextual correlations across large RF datasets before downstream analysis.
Phase I - Feasibility demonstrated with the Navy.
Phase II - Integrated prototype development.
Next step - Testing in relevant Navy environments.
Earlier Navy demonstrations validated significant reductions in RF storage requirements while maintaining high downstream analysis accuracy. Phase II expands the work with adaptive, self-learning capabilities.
The project advances CML from an AI approach demonstrated on accelerated computing toward a deployable capability for situational awareness in contested RF environments.
Case Study
Real-world applications demonstrating quantum advantage
AI & ML
Context Genomic, natural-language, and financial datasets can contain long-range correlations that are difficult to model efficiently with conventional approaches. Overview DARPA selected…
AI & ML
Context Tactical systems must fuse GPS, inertial, and vision data at the edge, often with limited connectivity and with signals that may…
National Security
Context Defense communications operate across crowded spectrum and rely on receivers that can work with existing electronic warfare and tactical radio systems.…
Talk with our team about the quantum systems and software that fit your mission, infrastructure, or research priorities.
