Skip to main content

k-space Neural computation with magnEtic exciTations

Objective

Artificial neural networks represent a key component of neuro-inspired computing for non-Boolean computational tasks. They emulate the brain by using nonlinear elements acting as neurons that are interconnected through artificial synapses. However, such physical implementations face two major challenges. First, interconnectivity is often constrained because of limits in lithography techniques and circuit architecture design; connections are limited to 100s, compared with 10000s in the human brain. Second, changing the weight of these individual interconnects dynamically requires additional memory elements attached to these links.

Here, we propose an innovative architecture to circumvent these issues. It is based on the idea that dynamical hyperconnectivity can be implemented not in real space but in reciprocal or k-space. To demonstrate this novel approach we have selected ferromagnetic nanostructures in which populations of spin waves – the elementary excitations – play the role of neurons. The key feature of magnetization dynamics is its strong nonlinearity, which, when coupled with external stimuli like applied fields and currents, translates into two useful features: (i) nonlinear interactions through exchange and dipole-dipole interactions couple potentially all spin wave modes together, thereby creating high connectivity; (ii) the strength of the coupling depends on the population of each k mode, thereby allowing for synaptic weights to be modified dynamically. The breakthrough concept here is that real-space interconnections are not necessary to achieve hyper-connectivity or reconfigurable synaptic weights.
The final goal is to provide a proof-of-concept of a k-space neural network based on interacting spin waves in low-loss materials such as yttrium iron garnet (YIG). The relevant spin wave eigenmodes are in the GHz range and can be accessed by microwave fields and spin-orbit torques to achieve k-space Neural computation with magnEtic exciTations.

Field of science

  • /natural sciences/chemical sciences/inorganic chemistry/inorganic compounds
  • /natural sciences/computer and information sciences/artificial intelligence/computational intelligence

Call for proposal

H2020-FETOPEN-2018-2019-2020-01
See other projects for this call

Funding Scheme

RIA - Research and Innovation action

Coordinator

CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE CNRS
Address
Rue Michel Ange 3
75794 Paris
France
Activity type
Research Organisations
EU contribution
€ 1 049 862,50

Participants (6)

AGENCIA ESTATAL CONSEJO SUPERIOR DEINVESTIGACIONES CIENTIFICAS
Spain
EU contribution
€ 295 787,50
Address
Calle Serrano 117
28006 Madrid
Activity type
Research Organisations
COMMISSARIAT A L ENERGIE ATOMIQUE ET AUX ENERGIES ALTERNATIVES
France
EU contribution
€ 449 993,75
Address
Rue Leblanc 25
75015 Paris 15
Activity type
Research Organisations
WESTFAELISCHE WILHELMS-UNIVERSITAET MUENSTER
Germany
EU contribution
€ 349 437,50
Address
Schlossplatz 2
48149 Muenster
Activity type
Higher or Secondary Education Establishments
C.R.E.A.T.E. CONSORZIO DI RICERCA PER L'ENERGIA L AUTOMAZIONE E LE TECNOLOGIE DELL'ELETTROMAGNETISMO
Italy
EU contribution
€ 301 090
Address
Via Claudio 21
80125 Napoli
Activity type
Research Organisations
PAZMANY PETER KATOLIKUS EGYETEM
Hungary
EU contribution
€ 214 500
Address
Szentkiralyi Utca 28
1088 Budapest
Activity type
Higher or Secondary Education Establishments
THALES
France
EU contribution
€ 375 330
Address
Tour Carpe Diem Place Des Corolles Esplanade Nord
92400 Courbevoie
Activity type
Private for-profit entities (excluding Higher or Secondary Education Establishments)