METHOD AND SYSTEM FOR STOCHASTIC INFERENCE BETWEEN MULTIPLE RANDOM VARIABLES VIA COMMON REPRESENTATION

Provided are a method and a system for stochastic inference between multiple random variables via common representation. The method includes developing a joint latent variable model having a first variable, a second variable, and a joint latent variable representing common information between the fi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LEE JUNG WON, RYU JONG HA, CHOI YOO JIN, EL KHAMY MOSTAFA
Format: Patent
Sprache:eng ; kor
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Provided are a method and a system for stochastic inference between multiple random variables via common representation. The method includes developing a joint latent variable model having a first variable, a second variable, and a joint latent variable representing common information between the first and second variables, generating a variational posterior of the joint latent variable model, training the variational posterior, and performing inference of the first variable from the second variable based on the variational posterior. 공통 표현을 통한 다수의 랜덤 변수 사이의 확률론적 추론을 위한 방법 및 시스템이 제공된다. 방법은, 제1 변수, 제2 변수 및 제1 변수와 제2 변수 사이의 공통 정보(common information)를 나타내는 결합 잠재 변수(joint latent variable)를 포함하는 결합 잠재 변수 모델(joint latent variable model)을 개발하고, 결합 잠재 변수 모델의 변분 사후확률(variational posterior)을 생성하고, 변분 사후확률을 훈련하고, 변분 사후확률을 기초로 하여 제2 변수로부터 제1 변수의 추론(inference)을 수행하는 것을 포함한다.