Research Focus Areas

A3D3 aims to construct the knowledge essential for real-time applications of artificial intelligence in three fields of science: high energy physics, multi-messenger astrophysics, systems neuroscience heterogenous systems and targeted systems. The institute aims to develop customized AI solutions to process large datasets in real time, significantly enhancing the potential for discovery.

Hardware and Algorithm Codevelopment

Developing AI methods to encode non-lattice-structured data is one main challenge in current AI systems.

High Energy Physics

Build tools to process LHC collisions occurring 40 million times per second data in real-time using AI.

Systems Neuroscience

Discover the computations that brain-wide neural networks perform to process sensory and motor information during behavior by using high-throughput and low-latency AI algorithms to process.

Heterogenous systems

Study a mixture of hardware resources like CPU, GPU and FPGA required for ML science pipelines.

Multi-messenger Astrophysics

Process the data from telescopes, neutrino detectors, and gravitational-wave detectors to identify astronomical events corresponding to the most violent phenomena in the Cosmos.

Targeted systems

Develop common tools for deploying ML algorithms in dedicated science experiment systems implemented in FPGAs and ASICs.