Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020069533 - METHOD, MACHINE-READABLE MEDIUM AND SYSTEM TO PARAMETERIZE SEMANTIC CONCEPTS IN A MULTI-DIMENSIONAL VECTOR SPACE AND TO PERFORM CLASSIFICATION, PREDICTIVE, AND OTHER MACHINE LEARNING AND AI ALGORITHMS THEREON

Publication Number WO/2020/069533
Publication Date 02.04.2020
International Application No. PCT/US2019/053914
International Filing Date 30.09.2019
IPC
G06F 7/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
7Methods or arrangements for processing data by operating upon the order or content of the data handled
G06F 17/00 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
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
G10L 13/08 2013.01
GPHYSICS
10MUSICAL INSTRUMENTS; ACOUSTICS
LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
13Speech synthesis; Text to speech systems
08Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
CPC
G06K 9/6257
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
6257characterised by the organisation or the structure of the process, e.g. boosting cascade
G06K 9/6288
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6288Fusion techniques, i.e. combining data from various sources, e.g. sensor fusion
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
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
G06N 5/02
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
5Computer systems using knowledge-based models
02Knowledge representation
Applicants
  • BRAINWORKS [US]/[US]
  • ALVELDA, Philip [US]/[US]
Inventors
  • ALVELDA, Philip
Agents
  • JALALI, Laleh
Priority Data
62/739,20729.09.2018US
62/739,20829.09.2018US
62/739,21029.09.2018US
62/739,28730.09.2018US
62/739,29730.09.2018US
62/739,30130.09.2018US
62/739,36401.10.2018US
62/739,86402.10.2018US
62/739,89502.10.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) METHOD, MACHINE-READABLE MEDIUM AND SYSTEM TO PARAMETERIZE SEMANTIC CONCEPTS IN A MULTI-DIMENSIONAL VECTOR SPACE AND TO PERFORM CLASSIFICATION, PREDICTIVE, AND OTHER MACHINE LEARNING AND AI ALGORITHMS THEREON
(FR) PROCÉDÉ, SUPPORT LISIBLE PAR MACHINE ET SYSTÈME PERMETTANT DE PARAMÉTRER DES CONCEPTS SÉMANTIQUES DANS UN ESPACE VECTORIEL MULTIDIMENSIONNEL ET D'EFFECTUER UNE CLASSIFICATION, UNE PRÉDICTION ET D'AUTRES ALGORITHMES D'APPRENTISSAGE AUTOMATIQUE ET D'IA
Abstract
(EN)
A computer-implemented method, computer system and machine readable medium. The method is to implement a training model to be used by a neural network-based computing system to perform distributed computation regarding semantic concepts. A training model corresponding to a data structure to be used by the neural network-based computing system corresponds to a Distributed Knowledge Graph (DKG) defined by a plurality of nodes each representing a respective one of a plurality of semantic concepts that are based at least in part on existing data, each of the nodes represented by a characteristic distributed pattern of activity levels for respective meta-semantic nodes (MSNs), the MSNs for said each of the nodes defining a standard basis vector to designate a semantic concept, wherein standard basis vectors for respective ones of the nodes together define a continuous vector space of the DKG.
(FR)
L'invention concerne un procédé mis en œuvre par ordinateur, un système informatique et un support lisible par machine. Le procédé consiste à mettre en œuvre un modèle d'apprentissage à utiliser par un système informatique basé sur un réseau neuronal permettant d'effectuer un calcul distribué concernant des concepts sémantiques. Un modèle d'apprentissage correspondant à une structure de données à utiliser par le système informatique basé sur un réseau neuronal correspond à un graphe de connaissances distribué (DKG) défini par une pluralité de nœuds représentant chacun un concept respectif d'une pluralité de concepts sémantiques qui sont basés au moins en partie sur des données existantes, chacun des nœuds étant représenté par un motif distribué caractéristique de niveaux d'activité de nœuds méta-sémantiques respectifs (MSN), les MSN de chacun desdits nœuds définissant un vecteur de base standard permettant de désigner un concept sémantique, des vecteurs de base standard de chacun des nœuds définissant ensemble un espace vectoriel continu du DKG.
Latest bibliographic data on file with the International Bureau