Processing

Please wait...

Settings

Settings

Goto Application

1. WO2017136104 - SPIKING MULTI-LAYER PERCEPTRON

Publication Number WO/2017/136104
Publication Date 10.08.2017
International Application No. PCT/US2017/012730
International Filing Date 09.01.2017
Chapter 2 Demand Filed 04.12.2017
IPC
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
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
CPC
G06F 11/0721
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
11Error detection; Error correction; Monitoring
07Responding to the occurrence of a fault, e.g. fault tolerance
0703Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
0706the processing taking place on a specific hardware platform or in a specific software environment
0721within a central processing unit [CPU]
G06F 11/079
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
11Error detection; Error correction; Monitoring
07Responding to the occurrence of a fault, e.g. fault tolerance
0703Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
079Root cause analysis, i.e. error or fault diagnosis
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 3/084
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
084Back-propagation
Applicants
  • QUALCOMM INCORPORATED [US]/[US]
Inventors
  • O'CONNOR, Peter
  • WELLING, Max
Agents
  • LENKIN, Alan M.
  • LUTZ, Joseph
  • CROSBY, Cornell D.
  • PARTOW-NAVID, Puya
  • BARZILAY, Ilan N.
  • FASHU-KANU, Alvin V.
Priority Data
15/252,15130.08.2016US
62/291,40904.02.2016US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SPIKING MULTI-LAYER PERCEPTRON
(FR) IMPULSION DE PERCEPTRON À MULTIPLES COUCHES
Abstract
(EN)
A method of training a neural network with back propagation includes generating error events representing a gradient of a cost function for the neural network. The error events may be generated based on a forward pass through the neural network resulting from input events, weights of the neural network and events from a target signal. The method further includes updating the weights of the neural network based on the error events.
(FR)
L'invention concerne un procédé d'entraînement d'un réseau neuronal à rétropropagation qui consiste à générer des évènements d'erreur représentant un gradient d'une fonction de coût servant au réseau neuronal. Les évènements d'erreur peuvent être générés en fonction d'une passe avant par le réseau neuronal résultant d'évènements d'entrée, des poids du réseau neuronal et d'évènements d'un signal cible. Le procédé consiste en outre à mettre à jour les poids du réseau neuronal en fonction des évènements d'erreur.
Latest bibliographic data on file with the International Bureau