APPARATUS AND METHOD FOR ARTIFICIAL INTELLIGENCE NEURAL NETWORK BASED ON CO-EVOLVING NEURAL ORDINARY DIFFERENTIAL EQUATIONS - IND ACADEMIC COOPERATION FOUNDATION YONSEI UNIV

Title:

APPARATUS AND METHOD FOR ARTIFICIAL INTELLIGENCE NEURAL NETWORK BASED ON CO-EVOLVING NEURAL ORDINARY DIFFERENTIAL EQUATIONS

Document Type and Number:

Japanese Patent JP2023090591

Kind Code:

A

Abstract:

To provide an apparatus and method for an artificial intelligence neural network based on co-evolving neural ordinary differential equations.SOLUTION: An apparatus for an artificial intelligence neural network based on co-evolving neural ordinary differential equations (NODEs) includes: a main NODE module configured to provide a downstream machine learning task; and an attention NODE module configured to receive the downstream machine learning task and provide attention to the main NODE module. The main NODE module and the attention NODE module may influence each other over time so that the main NODE module outputs a multivariate time-series value at a given time for an input sample (x).SELECTED DRAWING: Figure 5

Inventors:

PARK NO SEONG
JHIN SHEO YON
JO MIN JU
KONG TAE YONG
JEON JIN SUNG

Application Number:

JP2021215104A

Publication Date:

June 29, 2023

Filing Date:

December 28, 2021

Export Citation:

Click for automatic bibliography generation Help

Assignee:

IND ACADEMIC COOPERATION FOUNDATION YONSEI UNIV

International Classes:

G06N3/04; G06N3/08

Attorney, Agent or Firm:

Patent Attorney Corporation Kyosei International Patent Office

Previous Patent: ROAD CONDITION DATA PROCESSING APPARATUS AND METHOD

Next Patent: OCT-GAN (Neural ODE-based Conditional Tabular Generative Adversarial Networks) device and OCT-GAN me...