Global Patent Index - EP 2825974 A4

EP 2825974 A4 20170405 - TAG-BASED APPARATUS AND METHODS FOR NEURAL NETWORKS

Title (en)

TAG-BASED APPARATUS AND METHODS FOR NEURAL NETWORKS

Title (de)

TAG-BASIERTE VORRICHTUNG UND VERFAHREN FÜR NEURONALE NETZWERKE

Title (fr)

APPAREIL ET PROCÉDÉS POUR DES RÉSEAUX NEURONAUX À BASE D'ÉTIQUETTES

Publication

EP 2825974 A4 20170405 (EN)

Application

EP 13760351 A 20130315

Priority

  • US 201213385933 A 20120315
  • US 2013032546 W 20130315

Abstract (en)

[origin: WO2013138778A1] Apparatus and methods for high-level neuromorphic network description (HLND) using tags. The framework may be used to define nodes types, define node-to-node connection types, instantiate node instances for different node types, and/or generate instances of connection types between these nodes. The HLND format may be used to define nodes types, define node-to-node connection types, instantiate node instances for different node types, dynamically identify and/or select network subsets using tags, and/or generate instances of one or more connections between these nodes using such subsets. To facilitate the HLND operation and disambiguation, individual elements of the network (e.g., nodes, extensions, connections, I/O ports) may be assigned at least one unique tag. The tags may be used to identify and/or refer to respective network elements. The HLND kernel may comprises an interface to Elementary Network Description.

IPC 8 full level

G06N 3/10 (2006.01); G06N 3/02 (2006.01); G06N 3/04 (2006.01)

CPC (source: CN EP)

G06N 3/04 (2013.01 - CN EP); G06N 3/10 (2013.01 - CN EP)

Citation (search report)

  • [A] US 2007192262 A1 20070816 - MARIANETTI RONALD II [US], et al
  • [XI] KORB T ET AL: "A declarative neural network description language", MICROPROCESSING AND MICROPROGRAMMING, ELSEVIER SCIENCE PUBLISHERS, BV., AMSTERDAM, NL, vol. 27, no. 1-5, 1 August 1989 (1989-08-01), pages 181 - 188, XP026658288, ISSN: 0165-6074, [retrieved on 19890801], DOI: 10.1016/0165-6074(89)90043-4
  • [A] CORNELIS ET AL: "Neurospaces:Towards automated model partitioning for parallel computers", NEUROCOMPUTING, ELSEVIER, AMSTERDAM, NL, vol. 70, no. 10-12, 29 April 2007 (2007-04-29), pages 2117 - 2121, XP022053054, ISSN: 0925-2312, DOI: 10.1016/J.NEUCOM.2006.10.140
  • [A] ALFRED STREY: "EpsiloNN - A Specification Language for the Efficient Parallel Simulation of Neural Networks", BIOLOGICAL AND ARTIFICIAL COMPUTATION: FROM NEUROSCIENCE TO TECHNOLOGY, 1 January 1997 (1997-01-01), pages 714 - 722, XP055350267, Retrieved from the Internet <URL:ftp://neuro.informatik.uni-ulm.de/ni/alfred/iwann97.ps.gz> [retrieved on 20170228]
  • [A] PADRAIG GLEESON ET AL: "NeuroML: a language for describing data driven models of neurons and networks with a high degree of biological detail (w/ supporting information)", PLOS COMPUTATIONAL BIOLOGY, vol. 6, no. 6, 17 June 2010 (2010-06-17), pages e1000815, XP055179294, DOI: 10.1371/journal.pcbi.1000815
  • See references of WO 2013138778A1

Designated contracting state (EPC)

AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

DOCDB simple family (publication)

WO 2013138778 A1 20130919; CN 104620236 A 20150513; CN 104620236 B 20190215; CN 106991475 A 20170728; EP 2825974 A1 20150121; EP 2825974 A4 20170405

DOCDB simple family (application)

US 2013032546 W 20130315; CN 201380025107 A 20130315; CN 201710217138 A 20130315; EP 13760351 A 20130315