Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020112025 - METHOD AND SYSTEM FOR GENERATING TRAINING DATA FOR A MACHINE LEARNING MODEL FOR PREDICTING PERFORMANCE IN ELECTRONIC DESIGN

Publication Number WO/2020/112025
Publication Date 04.06.2020
International Application No. PCT/SG2019/050579
International Filing Date 26.11.2019
IPC
G06F 30/30 2020.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
30Computer-aided design
30Circuit design
G06F 30/27 2020.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
30Computer-aided design
20Design optimisation, verification or simulation
27using machine learning, e.g. artificial intelligence, neural networks, support vector machines or training a model
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 20/00 2019.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06F 17/10 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
10Complex mathematical operations
CPC
G06F 30/27
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
30Computer-aided design [CAD]
20Design optimisation, verification or simulation
27using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
G06F 30/30
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
30Computer-aided design [CAD]
30Circuit design
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 3/02
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
Applicants
  • AGENCY FOR SCIENCE, TECHNOLOGY AND RESEARCH [SG]/[SG]
Inventors
  • DUTTA, Rahul
  • SALAHUDDIN, Raju
  • CHAI, Kevin Tshun Chuan
Agents
  • VIERING, JENTSCHURA & PARTNER LLP
Priority Data
10201810572P26.11.2018SG
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) METHOD AND SYSTEM FOR GENERATING TRAINING DATA FOR A MACHINE LEARNING MODEL FOR PREDICTING PERFORMANCE IN ELECTRONIC DESIGN
(FR) PROCÉDÉ ET SYSTÈME DE PRODUCTION DE DONNÉES D'ENTRAÎNEMENT POUR UN MODÈLE À APPRENTISSAGE AUTOMATIQUE PERMETTANT DE PRÉDIRE LA PERFORMANCE EN CONCEPTION ÉLECTRONIQUE
Abstract
(EN)
There is provided a method of generating training data for a machine learning model for predicting performance in electronic design using at least one processor, the method including: generating a first set of training data based on a first set of input design parameters and an electronic design automation tool; generating a first covariance information associated with the first set of input design parameters based on the first set of training data; determining a second set of input design parameters based on the first covariance information; and generating a second set of training data based on the second set of input design parameters and the electronic design automation tool. There is also provided a corresponding system for generating training data for a machine learning model for predicting performance in electronic design.
(FR)
L'invention concerne un procédé de production de données d'entraînement pour un modèle à apprentissage automatique permettant de prédire la performance en conception électronique en utilisant au moins un processeur, le procédé consistant à : produire un premier ensemble de données d'entraînement en fonction d'un premier ensemble de paramètres de conception d'entrée et d'un outil d'automatisation de conception électronique; produire des premières informations de covariance associées au premier ensemble de paramètres de conception d'entrée en fonction du premier ensemble de données d'entraînement; déterminer un deuxième ensemble de paramètres de conception d'entrée en fonction des premières informations de covariance; et produire un deuxième ensemble de données d'entraînement en fonction du deuxième ensemble de paramètres de conception d'entrée et de l'outil d'automatisation de conception électronique. L'invention concerne également un système correspondant permettant de produire des données d'entraînement pour un modèle à apprentissage automatique permettant de prédire la performance en conception électronique.
Latest bibliographic data on file with the International Bureau