LGNEFeb 6, 2021

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

arXiv:2102.03626v14 citations
Originality Incremental advance
AI Analysis

This method offers a way for researchers and practitioners to efficiently identify inputs that lead to extreme outputs from their trained regression models, which is useful for understanding model behavior and optimizing system parameters.

This paper addresses the problem of finding the extremizing input for a trained neural network in regression tasks. It proposes a method that involves training an additional neural network with a specific loss function to achieve this, and also demonstrates how to incorporate input constraints.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes