Heterogeneous integration of imprecise memory devices to enable learning from a very small volume of noisy data

Project description

Technology with robust and responsive cognitive behaviour inspired by crickets

Separation of tasks is sometimes efficient – and sometimes not. Energy efficiency has become a key challenge in complex computing tasks. The separation of logic and memory in current electronic systems leads to inefficiency. Neuroscience has recently inspired powerful AI algorithms to enable effective real-time decision making based on a limited volume of noisy sensory data, something crickets due extremely well. The ERC-funded DIVERSE project will integrate principles from the cricket nervous system and resistive random-access memories (memristors) in an innovative hardware/software platform. With extremely high power efficiency and robust cognitive computing capabilities, the new technology will have applications in robotics, implantable medical devices and wearable electronics.

Fields of science

• engineering and technology › electrical engineering, electronic engineering, information engineering › electronic engineering
• natural sciences › biological sciences › neurobiology › cognitive neuroscience
• natural sciences › biological sciences › zoology › entomology
• natural sciences › computer and information sciences › artificial intelligence › computational intelligence

Programme(s)

• HORIZON.1.1 - European Research Council (ERC) Main Programme

Topic(s)

• ERC-2021-COG - ERC CONSOLIDATOR GRANTS

Call for proposal

ERC-2021-COG

See other projects for this call

Funding Scheme

ERC - Support for frontier research (ERC)

Coordinator

COMMISSARIAT A L ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES

Net EU contribution

€ 2 874 335,00

Address

Rue Leblanc 25
75015 Paris 15
France

Region

Ile-de-France › Ile-de-France › Paris

Activity type

Research Organisations

Links

Other funding

€ 0,00