Automation for Interpretable Machine Learning Through a Comparison of Loss Functions to Regularisers

TL;DR

This paper investigates using the Fit to Median Error measure in automated machine learning to enhance interpretability by regularising models to better reflect the underlying data relationships, demonstrated on ship power prediction.

Contribution

It introduces the use of Fit to Median Error as a regulariser in automated regression models, improving interpretability without compromising accuracy.

Findings

Models with Fit to Median Error better approximate ground truth.

Regularisation improves interpretability of neural networks.

No loss in conventional error metrics when using the new regulariser.

Abstract

To increase the ubiquity of machine learning it needs to be automated. Automation is cost-effective as it allows experts to spend less time tuning the approach, which leads to shorter development times. However, while this automation produces highly accurate architectures, they can be uninterpretable, acting as `black-boxes' which produce low conventional errors but fail to model the underlying input-output relationships -- the ground truth. This paper explores the use of the Fit to Median Error measure in machine learning regression automation, using evolutionary computation in order to improve the approximation of the ground truth. When used alongside conventional error measures it improves interpretability by regularising learnt input-output relationships to the conditional median. It is compared to traditional regularisers to illustrate that the use of the Fit to Median Error produces regression neural networks which model more consistent input-output relationships. The problem considered is ship power prediction using a fuel-saving air lubrication system, which is highly stochastic in nature. The networks optimised for their Fit to Median Error are shown to approximate the ground truth more consistently, without sacrificing conventional Minkowski-r error values.