Research Summaries

Back General-purpose Computing on a Neuromorphic Chip to Support Intelligence Processing at the Point of Collection

Fiscal Year 2020
Division Graduate School of Operational & Information Sciences
Department Computer Science
Investigator(s) Monaco, John V.
Sponsor Department of Defense Space (DoD)
Summary This work aims to develop the structures, abstractions, and design principles to achieve general-purpose computing on a neuromorphic chip in support of intelligence processing and reconnaissance missions. Neuromorphic computer architectures are inspired by properties of the mammalian brain that aim to overcome physical limitations of the von Neumann architecture. But programming these devices remains a challenge. Most current applications utilize neuromorphic chips only as accelerators for deep neural networks. This approach fails to address a substantial number of applications where general-purpose computing and well-defined behavior are required alongside machine learning, such as optimization and signal processing. It is necessary to investigate integrated symbolic and sub-symbolic computation on a single computer architecture as an enabling step toward processing intelligence at the point of collection.
Keywords
Publications Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal
Data Publications, theses (not shown) and data repositories will be added to the portal record when information is available in FAIRS and brought back to the portal