Twin neural network regression is a semi-supervised regression algorithm

Sebastian J. Wetzel

doi:10.1088/2632-2153/ac9885

Twin neural network regression is a semi-supervised regression algorithm

2022-10-20

6

OA

AI

S

Sebastian J. Wetzel *

DOI：10.1088/2632-2153/ac9885

Original

Original request for help

Save

Abstract

En 中文

Twin neural network regression (TNNR) is trained to predict differences between the target values of two different data points rather than the targets themselves. By ensembling predicted differences between the targets of an unseen data point and all training data points, it is possible to obtain a very accurate prediction for the original regression problem. Since any loop of predicted differences should sum to zero, loops can be supplied to the training data, even if the data points themselves within loops are unlabelled. Semi-supervised training improves TNNR performance, which is already state of the art, significantly.

Keywords:

artificial neural networks

regression

semi-supervised learning

Twin neural network regression is a semi-supervised regression algorithm

Abstract

Journal

Organization