DeepAI AI Chat
Log In Sign Up

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

by   A. I. Parkes, et al.

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.


page 1

page 2

page 3

page 4


Towards Error Measures which Influence a Learners Inductive Bias to the Ground Truth

Artificial intelligence is applied in a range of sectors, and is relied ...

Deep Unsupervised Drum Transcription

We introduce DrummerNet, a drum transcription system that is trained in ...

Error Correcting Algorithms for Sparsely Correlated Regressors

Autonomy and adaptation of machines requires that they be able to measur...

Learning Two-layer Neural Networks with Symmetric Inputs

We give a new algorithm for learning a two-layer neural network under a ...

Correctness Verification of Neural Networks

We present the first verification that a neural network produces a corre...

Modelling stochastic time delay for regression analysis

Systems with stochastic time delay between the input and output present ...