Skip to main content
Aller à la page d’accueil de la Commission européenne (s’ouvre dans une nouvelle fenêtre)
français français
CORDIS - Résultats de la recherche de l’UE
CORDIS
Contenu archivé le 2024-05-18

Attend-to-learn and learn-to-attend with neuromorphic, analogue VLSI

Objectif

A system for memory-guided perception on the basis of neuromorphic VLSI technology will be built. It will combine multiple VLSI chips with a unique communication infrastructure (address-event-representation, AER) that provides a technical realisation of biological many-to-many connectivity. The aim of the system is to perform classification and match-to-sample tasks in real time on selected types of natural images and sounds. The system will emulate the mutually beneficial interaction between attention and learning found in humans: attention accelerates learning ('attend-to-learn') and learning guides attention ('learn-to-attend'). To verify these and other emergent behaviours, synthetic stimuli and benchmark tests adapted from visual and auditory psychophysics will be used. Thus it will be possible to directly compare at every stage system and human performance. A system for memory-guided perception on the basis of neuromorphic VLSI technology will be built. It will combine multiple VLSI chips with a unique communication infrastructure (address-event-representation, AER) that provides a technical realisation of biological many-to-many connectivity. The aim of the system is to perform classification and match-to-sample tasks in real time on selected types of natural images and sounds. The system will emulate the mutually beneficial interaction between attention and learning found in humans: attention accelerates learning ('attend-to-learn') and learning guides attention ('learn-to-attend'). To verify these and other emergent behaviours, synthetic stimuli and benchmark tests adapted from visual and auditory psychophysics will be used. Thus it will be possible to directly compare at every stage system and human performance.

OBJECTIVES
- Design visual and auditory feature spaces that efficiently represent certain types of dynamic natural images and sounds (e.g. rippling wave patters, speech);
- Conduct psychophysical experiments with human observers to demonstrate human 'object attention' in the context of synthetic and natural stimuli that are well represented by the chosen feature spaces (visual and auditory);
- Develop a saliency network that approaches human performance on figure-ground segregation and multiple-object tracking with the saliency network;
- Develop an associative network whose memory performance suffices for complex synthetic and natural images as represented by the chosen feature spaces;
- Couple saliency and associative networks to achieve emergent behaviours 'attend-to-learn', 'learn-to-attend', and 'multi-stable perception' with synthetic benchmark stimuli;
- Achieve and disseminate a stable and versatile communication infrastructure for neuromorphic, analogue VLSI devices.
- Reach new level of complexity and performance with neuromorphic, analogue VLSI, and demonstrate the technological promise of this approach;
- Approach human performance on classification and match-to-sample tasks with plurality of natural images and sounds that are well represented by the chosen feature spaces.

DESCRIPTION OF WORK
Management and documentation (WP0): Coordination and documentation.
Visual (WP1) and auditory (WP2) input and feature spaces: Collect natural images and sounds, prepare benchmark tests, measure human performance. Visual features are sensitive to orientation and direction of motion (~300 total). Auditory features are sensitive to pitch, formants, and spectral drift.
Saliency network - simulation, testing (WP3) and hardware (WP7): Simulate, test, and build 'saliency network' of ~1000 integrate-and-fire neurones and ~16000 static synapses to represent feature activity. Recurrent excitation and inhibition mediate 'saliency', 'attention tracking' and 'onset binding'. Produce 2 or 3 chip generations, joining 4+ chips with AER communication.
Associative network - simulation, testing (WP4) and hardware (WP8): Simulate, test, and build 'associative network' of ~1000 integrate-and-fire neurones and ~30000 dynamic synapses. Hebbian potentiation and homo-synaptic depression associates features of sensory objects. Produce 2 or 3 chip generations.
Link module and emergent behaviours: simulation, testing (WP5) and hardware (WP6): Develop, build, and test a reciprocal link between saliency and associative networks. Test alternative architectures for emergent behaviours ('attend-to-learn', 'learn-to-attend', 'multi-stable perception'). Improve AER infrastructure and consider alternative architectures.
Natural images and response decoding (WP9): Compare system and human performance on natural images and sounds in classification and match-to-sample tasks. Predict system performance and information flow from response distributions.
Technology dissemination (WP11): Provide support, documentation, and hardware components to other groups. Improve AER infrastructure and increase bandwidth.

Champ scientifique (EuroSciVoc)

CORDIS classe les projets avec EuroSciVoc, une taxonomie multilingue des domaines scientifiques, grâce à un processus semi-automatique basé sur des techniques TLN. Voir: Le vocabulaire scientifique européen.

Ce projet n'a pas encore été classé par EuroSciVoc.
Proposez les domaines scientifiques qui vous semblent les plus pertinents et aidez-nous à améliorer notre service de classification.

Vous devez vous identifier ou vous inscrire pour utiliser cette fonction

Programme(s)

Programmes de financement pluriannuels qui définissent les priorités de l’UE en matière de recherche et d’innovation.

Thème(s)

Les appels à propositions sont divisés en thèmes. Un thème définit un sujet ou un domaine spécifique dans le cadre duquel les candidats peuvent soumettre des propositions. La description d’un thème comprend sa portée spécifique et l’impact attendu du projet financé.

Appel à propositions

Procédure par laquelle les candidats sont invités à soumettre des propositions de projet en vue de bénéficier d’un financement de l’UE.

Données non disponibles

Régime de financement

Régime de financement (ou «type d’action») à l’intérieur d’un programme présentant des caractéristiques communes. Le régime de financement précise le champ d’application de ce qui est financé, le taux de remboursement, les critères d’évaluation spécifiques pour bénéficier du financement et les formes simplifiées de couverture des coûts, telles que les montants forfaitaires.

CSC - Cost-sharing contracts

Coordinateur

OTTO-VON-GUERICKE-UNIVERSITAET MAGDEBURG
Contribution de l’UE
Aucune donnée
Adresse
UNIVERSITAETSPLATZ 2
39106 MAGDEBURG
Allemagne

Voir sur la carte

Coût total

Les coûts totaux encourus par l’organisation concernée pour participer au projet, y compris les coûts directs et indirects. Ce montant est un sous-ensemble du budget global du projet.

Aucune donnée

Participants (5)

Mon livret 0 0