Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020112105 - EVENT-BASED PROCESSING USING THE OUTPUT OF A DEEP NEURAL NETWORK

Publication Number WO/2020/112105
Publication Date 04.06.2020
International Application No. PCT/US2018/062876
International Filing Date 28.11.2018
IPC
G06N 3/04 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
G06N 3/08 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
CPC
G06N 3/04
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
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
Applicants
  • HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P. [US]/[US]
Inventors
  • ATHREYA, Madhu Sudan
  • LEWIS, M. Anthony
Agents
  • WOODWORTH, Jeffrey C.
  • AUSTIN, Wesley L.
Priority Data
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) EVENT-BASED PROCESSING USING THE OUTPUT OF A DEEP NEURAL NETWORK
(FR) TRAITEMENT BASÉ SUR DES ÉVÈNEMENTS UTILISANT LA SORTIE D'UN RÉSEAU NEURONAL PROFOND
Abstract
(EN)
Examples for event-based processing using the output of a deep neural network are described herein. In some examples, event format data may be provided to a spiking neural network (SNN). The SNN may perform processing on the event format data. The SNN may be trained for processing the event format data based on an output of a deep neural network (DNN) trained for processing of sensing data.
(FR)
L'invention concerne des exemples pour le traitement basé sur des évènements utilisant la sortie d'un réseau neuronal profond. Dans certains exemples, des données en format d'évènement peuvent être fournies à un réseau neuronal impulsionnel (SNN). Le SNN peut effectuer un traitement sur les données en format d'évènement. Le SNN peut être entraîné pour traiter les données en format d'évènement en fonction d'une sortie d'un réseau neuronal profond (DNN) entraîné pour le traitement de données de détection.
Latest bibliographic data on file with the International Bureau