Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and apparatus for learning stochastic inference model between multiple stochastic variables

A technology of random variables and latent variables, applied in neural learning methods, inference methods, biological neural network models, etc., can solve the problems of difficult access to paired data and high generation costs

Pending Publication Date: 2021-10-19
SAMSUNG ELECTRONICS CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in some applications, paired data are not readily available and can be expensive to generate

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and apparatus for learning stochastic inference model between multiple stochastic variables
  • Method and apparatus for learning stochastic inference model between multiple stochastic variables
  • Method and apparatus for learning stochastic inference model between multiple stochastic variables

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The detailed description set forth below in conjunction with the accompanying drawings is intended as a description of exemplary embodiments of systems and methods for learning a stochastic inference model among multiple random variables with unpaired data provided in accordance with the present disclosure, and is not intended to represent the only form in which this disclosure may be made or utilized. This description sets forth the features of the disclosure in conjunction with the illustrated embodiments. It should be understood, however, that the same or equivalent functions and structures can be accomplished by different embodiments, and such different embodiments are also intended to be included within the scope of the present disclosure. As indicated elsewhere herein, like element numbers are intended to refer to like elements or features.

[0042] As noted above, in various applications, starting from distributions that approximate the distributions of two rand...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention relates to a system and method for operating a neural network. In some embodiments, the neural network includes a variational autoencoder, and the training of the neural network includes training the variational autoencoder with a plurality of samples of a first random variable and a plurality of samples of a second random variable, wherein the plurality of samples of the first random variable and the plurality of samples of the second random variable are unpaired. The training of the neural network also includes updating the weights in the neural network based on a first loss function, wherein the first loss function is based on a measure of deviation from consistency between a conditional generation path from the first random variable to the second random variable, and a conditional generation path from the second random variable to the first random variable.

Description

[0001] Cross References to Related Applications [0002] This application claims priority and the benefit of U.S. Provisional Application No. 63 / 008294, entitled "METHOD AND APPARATUS FORLEARNING STOCHASTIC INFERENCE MODELS BETWEEN MULTIPLE RANDOM VARIABLES WITHUNPAIRED DATA," filed April 10, 2020, the entire contents of which are incorporated by reference into this article. technical field [0003] One or more aspects of embodiments according to the present disclosure relate to machine learning, and more particularly to stochastic inference models among a plurality of random variables. Background technique [0004] In various applications, it may be advantageous for a machine learning system to perform conditional or joint generation. Paired data can be used to train machine learning models to perform these tasks. However, in some applications, paired data are not readily available and can be expensive to generate. [0005] Accordingly, there is a need for an improved sy...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/04G06N3/08G06F18/2132G06N3/047G06N3/045G06N3/063G06N5/04G06N7/01G06N3/088
Inventor 柳淙夏李正元M.埃尔-哈米崔裕镇金映杆
Owner SAMSUNG ELECTRONICS CO LTD