Log In Sign Up

Twin Neural Network Regression

by   Sebastian J. Wetzel, et al.

We introduce twin neural network (TNN) regression. This method predicts differences between the target values of two different data points rather than the targets themselves. The solution of a traditional regression problem is then obtained by averaging over an ensemble of all predicted differences between the targets of an unseen data point and all training data points. Whereas ensembles are normally costly to produce, TNN regression intrinsically creates an ensemble of predictions of twice the size of the training set while only training a single neural network. Since ensembles have been shown to be more accurate than single models this property naturally transfers to TNN regression. We show that TNNs are able to compete or yield more accurate predictions for different data sets, compared to other state-of-the-art methods. Furthermore, TNN regression is constrained by self-consistency conditions. We find that the violation of these conditions provides an estimate for the prediction uncertainty.


page 1

page 2

page 3

page 4


Twin Neural Network Regression is a Semi-Supervised Regression Algorithm

Twin neural network regression (TNNR) is a semi-supervised regression al...

How to get the most out of Twinned Regression Methods

Twinned regression methods are designed to solve the dual problem to the...

Systematic Ensemble Learning for Regression

The motivation of this work is to improve the performance of standard st...

Confident Neural Network Regression with Bootstrapped Deep Ensembles

With the rise of the popularity and usage of neural networks, trustworth...

Learning Deep Neural Networks under Agnostic Corrupted Supervision

Training deep neural models in the presence of corrupted supervision is ...

KNN Ensembles for Tweedie Regression: The Power of Multiscale Neighborhoods

Very few K-nearest-neighbor (KNN) ensembles exist, despite the efficacy ...

Prediction of infectious disease epidemics via weighted density ensembles

Accurate and reliable predictions of infectious disease dynamics can be ...