Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020198132 - RESIDUAL SEMI-RECURRENT NEURAL NETWORKS

Publication Number WO/2020/198132
Publication Date 01.10.2020
International Application No. PCT/US2020/024196
International Filing Date 23.03.2020
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
CPC
G01N 33/5008
GPHYSICS
01MEASURING; TESTING
NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
33Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
48Biological material, e.g. blood, urine
50Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
5005involving human or animal cells
5008for testing or evaluating the effect of chemical or biological compounds, e.g. drugs, cosmetics
G06N 3/0445
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
0445Feedback networks, e.g. hopfield nets, associative networks
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 3/063
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
Applicants
  • SANOFI [FR]/[FR]
Inventors
  • TANG, Qi
  • QI, Youran
Agents
  • HAMLIN, Michael R.
Priority Data
19305611.613.05.2019EP
62/824,89527.03.2019US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) RESIDUAL SEMI-RECURRENT NEURAL NETWORKS
(FR) RÉSEAUX NEURONAUX SEMI-RÉCURRENTS RÉSIDUELS
Abstract
(EN)
Residual semi-recurrent neural networks (RSNN) can be configured to receive both time invariant input and time variant input data to generate one or more time series predictions. The time invariant input can be processed by a multilayer perceptron of the RSNN. The output of the multilayer perceptron can be used as an initial state for a recurrent neural network unit of the RSNN. The recurrent neural network unit can also receive time invariant input, and process the time invariant input with the time invariant input to generate an output. The outputs of the multilayer perceptron and the recurrent neural network unit can be combined to generate the one or more time series predictions.
(FR)
L'invention concerne des réseaux neuronaux semi-récurrents résiduels (RSNN) pouvant être configurés pour recevoir aussi bien des données d'entrée invariantes dans le temps que des données d'entrée variantes dans le temps pour générer une ou plusieurs prédictions de série temporelle. L'entrée invariante dans le temps peut être traitée par un perceptron multicouche des RSNN. La sortie du perceptron multicouche peut être utilisée comme état initial pour une unité de réseau neuronal récurrent des RSNN. L'unité de réseau neuronal récurrent peut également recevoir une entrée invariante dans le temps, et traiter l'entrée invariante dans le temps avec l'entrée invariante dans le temps pour générer une sortie. Les sorties du perceptron multicouche et de l'unité de réseau neuronal récurrent peuvent être combinées pour générer lesdites prédictions de série temporelle.
Latest bibliographic data on file with the International Bureau