Unsupervised learning method for general inverse problem and apparatus therefor
AssigneeKorea Advanced Institute of Science and Technology
InventorsJongChul Ye, Byeongsu Sim, Gyutaek Oh
Life of this patent
Estimating the term…
Abstract
Disclosed are an unsupervised learning method and an apparatus therefor applicable to general inverse problems. An unsupervised learning method applicable to inverse problems includes receiving a training data set and training an unsupervised learning-based neural network generated based on an optimal transport theory and a penalized least square (PLS) approach using the training data set, wherein the receiving of the training data set includes receiving the training data set including unmatched data.
Claims15
An unsupervised learning method applicable to inverse problems, comprising:
- receiving a training data set;
- and
- training an unsupervised learning-based neural network generated based on an optimal transport theory and a penalized least square (PLS) approach using the training data set.
The unsupervised learning method of claim 7, wherein the conversion unit includes a linear convolution layer corresponding to the point spread function.
An image processing method, comprising:
- receiving a first image;
- and
- reconstructing the first image as a second image corresponding to the first image using an unsupervised learning-based neural network generated based on an optimal transport theory and a penalized least square (PLS) approach.
An unsupervised learning apparatus applicable to inverse problems, comprising:
- a receiving unit configured to receive a training data set;
- and
- a training unit configured to train an unsupervised learning-based neural network generated based on an optimal transport theory and a penalized least square (PLS) approach using the training data set.
Dependencies are inferred from the claim text.