1. Two-Dimensional Oscillatory Neural Networks for EnergyTwo-Dimensional Oscillatory Neural Networks for Energy
E cient Neuromorphic ComputingE cient Neuromorphic Computing
Fact Sheet
Project informationProject information
Project descriptionProject description
Energy-e cient bio-inspired devices accelerate route to brain-like computingEnergy-e cient bio-inspired devices accelerate route to brain-like computing
Neuro-inspired computing employs technologies that enable brain-inspired computing hardware for more
e cient and adaptive intelligent systems. Mimicking the human brain and nervous system, these
computing architectures are excellent candidates for solving complex and large-scale associative learning
problems. The EU-funded NeurONN project will showcase a novel and alternative neuromorphic computing
paradigm based on energy-e cient devices and architectures. In the proposed neuro-inspired computing
architecture, information will be encoded in the phase of coupled oscillating neurons or oscillatory neural
networks. The VO2 metal-insulator transition devices will emulate biological neurons and are expected to
be 250 times more e cient that state-of-the-art digital CMOS-based oscillators. Their 2D memristors that
will emulate synapses are expected to be 330 times more e cient than the state-of-the-art.
ObjectiveObjective
Neuro-inspired computing architectures are one of the leading candidates to solve complex and large-
scale associative learning problems for AI applications. The two key building blocks for neuromorphic
computing are the neuron and the synapse, which form the distributed computing and memory units. In the
NeurONN project, we are proposing a novel neuro-inspired computing architecture where information is
Grant agreement ID: 871501Grant agreement ID: 871501
Status
Ongoing projectOngoing project
NeurONN
Start date
1 January 20201 January 2020
End date
31 December 202231 December 2022
Funded under:
H2020-EU.2.1.1.H2020-EU.2.1.1.
Coordinated by:
CENTRE NATIONAL DE LA RECHERCHECENTRE NATIONAL DE LA RECHERCHE
SCIENTIFIQUE CNRSSCIENTIFIQUE CNRS
FranceFrance
Overall budget:
€ 4 232 737,50
EU contribution
€ 4 232 737,50
2. encoded in the “phase” of coupled oscillating neurons or oscillatory neural networks (ONN). Speci cally,
VO2 metal-insulator transition (MIT) devices and 2D memristors will be developed as neurons and
synapses for hardware implementations. We predict VO2 MIT devices are up to 250X more energy e cient
than state of the art digital CMOS based oscillators, where 2D memristors are up to 330X more energy
e cient than state of the art TiO2 memristors. Moreover, the predicted energy e ciency gain of ONN
architecture vs state of the art spiking neural network (SNN) architecture is up to 40X. Thus, NeurONN will
showcase a novel and alternative energy e cient neuromorphic computing paradigm based on energy
e cient devices and architectures. Such ONN will demonstrate synchronization and coupling dynamics for
establishing collective learning behavior, in addition to desirable characteristics such as scaling, ultra-low
power computation, and high computing performance. NeurONN aims to develop the rst-ever ONN
hardware platform (targeting two demonstrators) and complete with an ONN design methodology toolbox
covering aspects from ONN architecture design to algorithms in order to facilitate adoption, testing and
experimentation of ONN demonstrator chips by all potential users to unleash the potential of ONN
technology.
CoordinatorCoordinator
Programme(s)Programme(s)
H2020-EU.2.1.1. - INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies -H2020-EU.2.1.1. - INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies -
Information and Communication Technologies (ICT)Information and Communication Technologies (ICT)
Topic(s)Topic(s)
ICT-06-2019 - Unconventional NanoelectronicsICT-06-2019 - Unconventional Nanoelectronics
Call for proposalCall for proposal
H2020-ICT-2019-2
See other projects for this callSee other projects for this call
Funding SchemeFunding Scheme
RIA - Research and Innovation action
CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE CNRSCENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE CNRS
Address
Rue Michel Ange 3Rue Michel Ange 3
75794 Paris75794 Paris
FranceFrance
Activity type
Research OrganisationsResearch Organisations
EU Contribution
€ 1 064 800€ 1 064 800
WebsiteWebsite
Contact the organisationContact the organisation
3. ParticipantsParticipants (5)
IBM RESEARCH GMBHIBM RESEARCH GMBH
SwitzerlandSwitzerland
EU Contribution
€ 763 687,50€ 763 687,50
Address
Saeumerstrasse 4Saeumerstrasse 4
8803 Rueschlikon8803 Rueschlikon
Activity type
Private for-pro t entitiesPrivate for-pro t entities
(excluding Higher or(excluding Higher or
Secondary EducationSecondary Education
Establishments)Establishments)
WebsiteWebsite
Contact the organisationContact the organisation
FRAUNHOFER GESELLSCHAFT ZUR FOERDERUNG DERFRAUNHOFER GESELLSCHAFT ZUR FOERDERUNG DER
ANGEWANDTEN FORSCHUNG E.V.ANGEWANDTEN FORSCHUNG E.V.
GermanyGermany
EU Contribution
€ 1 119 975€ 1 119 975
Address
Hansastrasse 27cHansastrasse 27c
80686 Munchen80686 Munchen
Activity type
Research OrganisationsResearch Organisations
WebsiteWebsite
Contact the organisationContact the organisation
AGENCIA ESTATAL CONSEJO SUPERIORAGENCIA ESTATAL CONSEJO SUPERIOR
DEINVESTIGACIONES CIENTIFICASDEINVESTIGACIONES CIENTIFICAS
SpainSpain
EU Contribution
€ 589 440€ 589 440
Address
Calle Serrano 117Calle Serrano 117
28006 Madrid28006 Madrid
Activity type
Research OrganisationsResearch Organisations
WebsiteWebsite
Contact the organisationContact the organisation
A I MERGENCEA I MERGENCE
FranceFrance
EU Contribution
€ 402 085€ 402 085
Address
16 Villa Robert Doisneau16 Villa Robert Doisneau
75013 Paris75013 Paris
Activity type
Private for-pro t entitiesPrivate for-pro t entities
(excluding Higher or(excluding Higher or
Secondary EducationSecondary Education
Establishments)Establishments)
Contact the organisationContact the organisation