Automation for Interpretable Machine Learning Through a Comparison of Loss Functions to Regularisers
This work addresses interpretability in automated ML for domain-specific applications like ship power prediction, but it is incremental as it builds on existing regularization methods.
The paper tackled the problem of uninterpretable automated machine learning models by introducing the Fit to Median Error measure to improve approximation of ground truth in regression tasks, showing that it produces more consistent input-output relationships without sacrificing conventional error values in ship power prediction.
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.