Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020139964 - THERMODYNAMIC NEURAL NETWORK

Publication Number WO/2020/139964
Publication Date 02.07.2020
International Application No. PCT/US2019/068603
International Filing Date 26.12.2019
IPC
G06N 3/02 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
G06N 3/04 2006.1
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 3/06 2006.1
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 3/063 2006.1
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
063using electronic means
G06N 3/08 2006.1
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 20/00 2019.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
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 3/082
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
082modifying the architecture, e.g. adding or deleting nodes or connections, pruning
G06N 7/005
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
7Computer systems based on specific mathematical models
005Probabilistic networks
Applicants
  • THE REGENTS OF THE UNIVERSITY OF CALIFORNIA [US]/[US]
Inventors
  • HYLTON, Todd
Agents
  • ZHANG, Li (Lily)
  • ADAMS, Lisa
  • ALLISON, William, F.
  • AMENDT, Kevin, C.
  • AZRIN, Linda, B.
Priority Data
62/786,24328.12.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) THERMODYNAMIC NEURAL NETWORK
(FR) RÉSEAU NEURONAL THERMODYNAMIQUE
Abstract
(EN)
A method may include training a thermodynamic neural network having a plurality of nodes interconnected by a plurality of edges. The training of the thermodynamic neural network may include determining an optimal organization of the thermodynamic neural network in which one or more charges are transferred through the thermodynamic neural network with a minimum quantity of residual charge remaining at each of the plurality of nodes. The trained thermodynamic neural network may be deployed to perform a cognitive task. The cognitive task may include the trained thermodynamic neural network receiving a first set of charges corresponding to an input sample and outputting a second set of charges corresponding to a decision associated with the input sample. Related systems and articles of manufacture, including computer program products, are also provided.
(FR)
L’invention concerne un procédé qui peut comprendre l'apprentissage d'un réseau neuronal thermodynamique ayant une pluralité de nœuds interconnectés par une pluralité de bords. L'apprentissage du réseau neuronal thermodynamique peut consister à déterminer une organisation optimale du réseau neuronal thermodynamique dans laquelle une ou plusieurs charges sont transférées à travers le réseau neuronal thermodynamique avec une quantité minimale de charge résiduelle restant au niveau de chacun de la pluralité de nœuds. Le réseau neuronal thermodynamique entraîné peut être déployé pour effectuer une tâche cognitive. La tâche cognitive peut comprendre la réception, par le réseau neuronal thermodynamique entraîné, d'un premier ensemble de charges correspondant à un échantillon d'entrée et la fourniture, par ledit réseau neuronal, d'un second ensemble de charges correspondant à une décision associée à l'échantillon d'entrée. L’invention concerne également des systèmes et des articles manufacturés associés, notamment des produits-programmes informatiques.
Latest bibliographic data on file with the International Bureau