Feedback
Settings

Settings

Goto Application

1. WO2013043610 - ELEMENTARY NETWORK DESCRIPTION FOR NEUROMORPHIC SYSTEMS

PermaLink
Publication Number WO/2013/043610
Publication Date 28.03.2013
International Application No. PCT/US2012/055933
International Filing Date 18.09.2012
Chapter 2 Demand Filed 12.07.2013
IPC
G06F 15/18 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
15Digital computers in general; Data processing equipment in general
18in which a program is changed according to experience gained by the computer itself during a complete run; Learning machines
CPC
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/049
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
049Temporal neural nets, e.g. delay elements, oscillating neurons, pulsed inputs
G06N 3/063
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
06Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
063using electronic means
G06N 3/088
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
088Non-supervised learning, e.g. competitive learning
G06N 3/105
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
10Simulation on general purpose computers
105Shells for specifying net layout
G06N 99/007
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
99Subject matter not provided for in other groups of this subclass
007Molecular computers, i.e. using inorganic molecules
Applicants
  • BRAIN CORPORATION [US]/[US] (AllExceptUS)
  • IZHIKEVICH, Eugene M. [RU]/[US] (US)
  • SZATMARY, Botond [HU]/[US] (US)
  • PETRE, Csaba [US]/[US] (US)
  • NAGESWARAN, Jayram Moorkanikara [IN]/[CN] (US)
  • PIEKNIEWSKI, Filip [PL]/[US] (US)
Inventors
  • IZHIKEVICH, Eugene M.
  • SZATMARY, Botond
  • PETRE, Csaba
  • NAGESWARAN, Jayram Moorkanikara
  • PIEKNIEWSKI, Filip
Agents
  • BLAYLOCK, Richard L.
Priority Data
13/239,12321.09.2011US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) ELEMENTARY NETWORK DESCRIPTION FOR NEUROMORPHIC SYSTEMS
(FR) DESCRIPTION DE RÉSEAU ÉLÉMENTAIRE POUR SYSTÈMES NEUROMORPHIQUES
front page image
Abstract
(EN) A simple format is disclosed and referred to as Elementary Network Description (END). The format can fully describe a large-scale neuronal model and embodiments of software or hardware engines to simulate such a model efficiently. The architecture of such neuromorphic engines is optimal for high-performance parallel processing of spiking networks with spike-timing dependent plasticity. Neuronal network and methods for operating neuronal networks comprise a plurality of units, where each unit has a memory and a plurality of doublets, each doublet being connected to a pair of the plurality of units. Execution of unit update rules for the plurality of units is order-independent and execution of doublet event rules for the plurality of doublets is order-independent.
(FR) L'invention concerne un format simple désigné sous le nom de description de réseau élémentaire (END). Le format peut décrire complètement un modèle neuronal à grande échelle et des modes de réalisation de moteurs logiciels ou matériels pour simuler efficacement un tel modèle. L'architecture de tels moteurs neuromorphiques est optimale pour le traitement parallèle à hautes performances de réseaux à impulsion avec une plasticité liée aux moments d'impulsion. Le réseau neuronal et les procédés de fonctionnement des réseaux neuronaux comprennent une pluralité d'unités, chaque unité comprenant une mémoire et une pluralité de doublets, chaque doublet étant connecté à une paire de la pluralité d'unités. L'exécution des règles de mise à jour d'unités pour la pluralité d'unités est indépendante de l'ordre et l'exécution des règles d'événements de doublets pour la pluralité de doublets est indépendante de l'ordre.
Related patent documents
US20130073495
Latest bibliographic data on file with the International Bureau
# -