Processing

Please wait...

Settings

Settings

Goto Application

1. WO2019246116 - APPARATUS AND METHOD FOR UTILIZING A PARAMETER GENOME CHARACTERIZING NEURAL NETWORK CONNECTIONS AS A BUILDING BLOCK TO CONSTRUCT A NEURAL NETWORK WITH FEEDFORWARD AND FEEDBACK PATHS

Publication Number WO/2019/246116
Publication Date 26.12.2019
International Application No. PCT/US2019/037758
International Filing Date 18.06.2019
IPC
G06N 3/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
G06N 3/02 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
G06N 3/06 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR 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
G06N 3/10 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
10Simulation on general purpose computers
G06N 3/12 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
12using genetic models
CPC
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 3/049
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 3/086
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
086using evolutionary programming, e.g. genetic algorithms
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
Applicants
  • ORBAI TECHNOLOGIES, INC. [US]/[US]
Inventors
  • OSTER, Brent Leonard
Agents
  • GALLIANI, William S.
  • ZIMMER, Kevin J.
Priority Data
62/687,17919.06.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) APPARATUS AND METHOD FOR UTILIZING A PARAMETER GENOME CHARACTERIZING NEURAL NETWORK CONNECTIONS AS A BUILDING BLOCK TO CONSTRUCT A NEURAL NETWORK WITH FEEDFORWARD AND FEEDBACK PATHS
(FR) APPAREIL ET PROCÉDÉ POUR UTILISER UN GÉNOME PARAMÈTRE CARACTÉRISANT DES CONNEXIONS DE RÉSEAU NEURONAL EN TANT QUE BLOC CONSTITUTIF POUR CONSTRUIRE UN RÉSEAU NEURONAL DOTÉ DE TRAJETS D'ACTION DIRECTE ET DE RÉTROACTION
Abstract
(EN)
A method of forming a neural network includes specifying layers of neural network neurons. A parameter genome is defined with numerical parameters characterizing connections between neural network neurons in the layers of neural network neurons, where the connections are defined from a neuron in a current layer to neurons in a set of adjacent layers, and where the parameter genome has a unique representation characterized by kilobytes of numerical parameters. Parameter genomes are combined into a connectome characterizing all connections between all neural network neurons in the connectome, where the connectome has in excess of millions of neural network neurons and billions of connections between the neural network neurons.
(FR)
L'invention concerne un procédé de formation d'un réseau neuronal, comprenant la spécification de couches de neurones de réseau neuronal. Un génome paramètre est défini avec des paramètres numériques caractérisant des connexions entre des neurones de réseau neuronal dans les couches de neurones de réseau neuronal, les connexions étant définies d'un neurone dans une couche actuelle à des neurones dans un ensemble de couches adjacentes, et le génome paramètre possédant une représentation unique caractérisée par des kilooctets de paramètres numériques. Des génomes paramètres sont combinés en un connectome caractérisant toutes les connexions entre tous les neurones de réseau neuronal du connectome, le connectome possédant plus que des millions de neurones de réseau neuronal et des milliards de connexions entre les neurones de réseau neuronal.
Also published as
Latest bibliographic data on file with the International Bureau