Extremal learning: extremizing the output of a neural network in regression problems

TL;DR

This paper introduces a method to efficiently find input extrema of trained neural networks in regression tasks by training an auxiliary neural network, with the ability to incorporate input constraints.

Contribution

It presents a novel approach to extremize neural network outputs by formulating it as a secondary training process, including constraint handling.

Findings

Effective extremization of neural network outputs demonstrated.

Incorporation of input constraints to limit extrapolation.

Implementation example provided using TensorFlow.

Abstract

Neural networks allow us to model complex relationships between variables. We show how to efficiently find extrema of a trained neural network in regression problems. Finding the extremizing input of an approximated model is formulated as the training of an additional neural network with a loss function that minimizes when the extremizing input is achieved. We further show how to incorporate additional constraints on the input vector such as limiting the extrapolation of the extremizing input vector from the original training data set. An instructional example of this approach using TensorFlow is included.