Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD FOR KNOWLEDGE DISTILLATION AND MODEL GENERATION
Document Type and Number:
WIPO Patent Application WO/2023/210914
Kind Code:
A1
Abstract:
The present techniques generally relate to a system and method for knowledge distillation between machine learning, ML, models. In particular, the present application relates to a computer-implemented method for training a condenser model to learn how to transfer knowledge between a teacher model and a student model, and using this trained condenser model to more quickly generate new student models.

More Like This:
WO/2023/071626FEDERATED LEARNING METHOD AND APPARATUS, AND DEVICE, STORAGE MEDIUM AND PRODUCT
JP7096653How to train a test measuring device and a test measuring device to propose a measurement
WO/2021/231317CLINICAL PREDICTOR BASED ON MULTIPLE MACHINE LEARNING MODELS
Inventors:
OZAY METE (GB)
Application Number:
PCT/KR2022/021496
Publication Date:
November 02, 2023
Filing Date:
December 28, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G06N20/20; G06V10/774; G10L15/06; G10L25/27
Domestic Patent References:
WO2020102887A12020-05-28
WO2020009652A12020-01-09
Foreign References:
US20210397954A12021-12-23
US20200401929A12020-12-24
KR102232138B12021-03-25
Attorney, Agent or Firm:
KIM, Tae-hun et al. (KR)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: CELL BALANCING METHOD AND BATTERY PACK EMPLOYING SAME

Next Patent: SCROLL COMPRESSOR AND MANUFACTURING METHOD THEREFOR