FRAMEWORK FOR CAUSAL LEARNING OF NEURAL NETWORKS

Title:

FRAMEWORK FOR CAUSAL LEARNING OF NEURAL NETWORKS

Document Type and Number:

WIPO Patent Application WO/2022/164299

Kind Code:

A1

Abstract:

Disclosed herein is the framework of causal cooperative nets that discovers the causal relationship between observational data in a dataset and a label of the observation thereof and trains each model with inference of a causal explanation, reasoning, and production. In the case of the supervised learning, neural networks are adjusted through the prediction of the label for observation inputs. On the other hand, a causal cooperative net includes an explainer, a reasoner, and a producer neural network models, receives an observation and a label as a pair, results multiple outputs, and calculates a set of losses of inference, generation, and reconstruction from the input and the outputs. The explainer, the reasoner, and the producer are adjusted by error propagation for each model obtained from the set of losses.

More Like This:

WO/2018/150083	A METHOD AND TECHNICAL EQUIPMENT FOR VIDEO PROCESSING
JP7035042	Simultaneous multitasking neural network model for multiple natural language processing (NLP) tasks
JP4201012	Data processing equipment, data processing methods, and programs

Inventors:

PARK JUN HO (KR)

Application Number:

PCT/KR2022/004553

Publication Date:

August 04, 2022

Filing Date:

March 30, 2022

Export Citation:

Click for automatic bibliography generation Help

Assignee:

PARK JUN HO (KR)

International Classes:

G06N3/04

Foreign References:

KR102037484B1	2019-10-28
US20190035387A1	2019-01-31
JP2019144779A	2019-08-29

Other References:

I-SHENG YANG: "A Loss-Function for Causal Machine-Learning", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 2 January 2020 (2020-01-02), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081571132
SCHOLKOPF BERNHARD; LOCATELLO FRANCESCO; BAUER STEFAN; KE NAN ROSEMARY; KALCHBRENNER NAL; GOYAL ANIRUDH; BENGIO YOSHUA: "Toward Causal Representation Learning", PROCEEDINGS OF THE IEEE, IEEE. NEW YORK., US, vol. 109, no. 5, 26 February 2021 (2021-02-26), US , pages 612 - 634, XP011851602, ISSN: 0018-9219, DOI: 10.1109/JPROC.2021.3058954

Attorney, Agent or Firm:

KEY IP&LAW FIRM (KR)

Download PDF:

View/Download PDF PDF Help

Previous Patent: HARDENED COMPOSITION AND PREPARATION METHOD THEREOF

Next Patent: FOCUSED ULTRASOUND IRRADIATION APPARATUS FOR LABORATORY ANIMAL USING THREE-DIMENSIONAL IMAGE DATA