Descrizione del progetto
Una rete neurale artificiale innovativa potrebbe apprendere fino a 10 milioni di volte più rapidamente rispetto a noi
Sviluppare reti neurali artificiali in grado di apprendere, elaborare e «pensare» come il cervello è una sorta di Santo Gral, con applicazioni quasi illimitate. I paradigmi di apprendimento profondo che sfruttano reti neurali artificiali gerarchiche multistrato, imitando la struttura del cervello, possono anche simularne la capacità di apprendere con l’esempio. Tali tecnologie hanno ottenuto successi straordinari, in alcuni casi superando persino i risultati degli esseri umani. Il progetto RadioSpin, finanziato dall’UE, intende dimostrare reti di apprendimento profondo che elaborano segnali di radiofrequenza e apprendono fino a 10 milioni di volte più velocemente rispetto a un cervello umano. Le applicazioni comparative della tecnologia verranno impiegate per la mammografia e il rilevamento delle impronte digitali con radiofrequenza nell’ambito dell’Internet degli oggetti (IoT, Internet of Things).
Obiettivo
The goal of RadioSpin is to build a hardware neural network that computes using neural dynamics as in the brain, has a deep layered architecture as in the neocortex, but runs and learns faster, by seven orders of magnitude. For this purpose, we will use ultrafast radio-frequency (RF) oscillators to imitate the rich, reconfigurable dynamics of biological neurons. Within the RadioSpin project, we will develop a new breed of nanosynapses, based on spintronics technology, that directly process the RF signals sent by neurons and interconnects them layer-wise. We will demonstrate and benchmark our concept by building a lab-scale prototype that co-integrates for the first time CMOS RF neurons with spintronic RF synapses. We will develop brain-inspired algorithms harnessing oscillations, synchrony and edge-of-chaos for computing and show that they can run on RadioSpin deep network RF technology. Finally, we will benchmark RadioSpin technology for biomedical and RF fingerprinting applications where fast and low energy consumption classification of RF signals are key.
To achieve its ambitious goals RadioSpin brings together frontier researchers along the entire chain of neuromorphic engineering, from material science (spintronic nanodevices), physics (non-linear dynamics), electronics (RF CMOS design), computer science (artificial intelligence algorithms), and microwave signal processing. Two innovative companies bring real-life use-cases (microwave mammography and IoT RF fingerprinting). The scientific experts are further complemented by experts in the field of innovation, commercial deployment and IP monetisation, as well as communication and public engagement.
Campo scientifico
- engineering and technologyelectrical engineering, electronic engineering, information engineeringinformation engineeringtelecommunicationsradio technologyradio frequency
- natural sciencescomputer and information sciencesinternetinternet of things
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsignal processing
- natural sciencesphysical scienceselectromagnetism and electronicsspintronics
- natural sciencescomputer and information sciencesartificial intelligencecomputational intelligence
Parole chiave
Programma(i)
Invito a presentare proposte
Vedi altri progetti per questo bandoBando secondario
H2020-FETPROACT-2020-01
Meccanismo di finanziamento
RIA - Research and Innovation actionCoordinatore
33000 Bordeaux
Francia