Scalable Analog Neural-networks (ScAN)
Closed Pre-Solicitation Posted
- Solicitation number
- HR001124S0022
- Agency
-
Defense Advanced Research Projects Agency
Department of Defense
- Responses due
- Set-aside
- No set-aside
Opportunity facts
- NAICS code
- 541715 Research and Development in the Physical, Engineering, and Life Sciences (except Nanotechnology and Biotechnology)
- Points of contact
-
- BAA Coordinator hr001124s0022@darpa.mil
Notice details come from SAM.gov. Updated .
About this opportunity
The Defense Advanced Research Projects Agency (DARPA) is soliciting innovative proposals for the research and development of scalable, robust, and power-efficient analog neural network (NN) architectures and circuits that can directly interface with analog sensor outputs. The proposed research should investigate approaches that enable revolutionary advances in science, devices, or systems, rather than evolutionary improvements to the existing state of practice. Key program requirements include demonstrating over 200x power efficiency gains in Phase 1 and over 2000x power efficiency gains in Phase 2, as well as meeting specified accuracy targets and fabricating and testing analog NN hardware. Proposals will be evaluated on scientific and technical merit, potential contribution to DARPA's mission, and cost realism. Proposals are due by September 9, 2024.
There is no set-aside designation for this opportunity. DARPA anticipates making multiple awards under this solicitation, with an anticipated funding source of 6.2 Applied Research. The program is unclassified and does not require security clearances. There is no budget cap, but cost realism is an evaluation factor. DARPA will provide benchmark datasets as government-furnished information to emulate analog sensor inputs.
Notice text
2 versions
Update #2 · Latest ·
The Defense Advanced Research Projects Agency (DARPA) is soliciting innovative proposals in the following technical areas: the research and development of scalable, robust, and power-efficient analog neural network (NN) architectures and circuits that could directly interface with the analog outputs of conventional sensors. Proposed research should investigate innovative approaches that enable revolutionary advances in science, devices, or systems. Specifically excluded is research that primarily results in evolutionary improvements to the existing state of practice including in-memory-compute (or compute-in-memory) device technology, non-volatile memory development, analog-digital conversion technology, digital accelerator technology, and general-purpose computing technology.
Update #1 ·
The Defense Advanced Research Projects Agency (DARPA) is soliciting innovative proposals in the following technical areas: the research and development of scalable, robust, and power-efficient analog neural network (NN) architectures and circuits that could directly interface with the analog outputs of conventional sensors. Proposed research should investigate innovative approaches that enable revolutionary advances in science, devices, or systems. Specifically excluded is research that primarily results in evolutionary improvements to the existing state of practice including in-memory-compute (or compute-in-memory) device technology, non-volatile memory development, analog-digital conversion technology, digital accelerator technology, and general-purpose computing technology.
Files
Show all 14
On GovTribe
Work this opportunity
- Track it in your pipeline
- Find teaming partners
- Similar opportunities
- Ask GovTribe AI about this opportunity