Related papers: Interpretable Faraday Complexity Classification

Machine-learning models have demonstrated great success in learning complex patterns that enable them to make predictions about unobserved data. In addition to using models for prediction, the ability to interpret what a model has learned…

Magnetic fields play vital roles in intracluster media (ICMs), but estimating their strengths and distributions from observations is a major challenge. Faraday rotation measures (RMs) are widely applied to this task, so it is critical to…

Feature selection of high-dimensional labeled data with limited observations is critical for making powerful predictive modeling accessible, scalable, and interpretable for domain experts. Spectroscopy data, which records the interaction…

The S-band Polarisation All Sky Survey (SPASS/ATCA) rotation measure (RM) catalogue is the largest broadband RM catalogue to date, increasing the RM density in the sparse southern sky. Through analysis of this catalogue, we report a…

Explaining complex or seemingly simple machine learning models is an important practical problem. We want to explain individual predictions from a complex machine learning model by learning simple, interpretable explanations. Shapley values…

Tree ensembles, such as random forests and boosted trees, are renowned for their high prediction performance. However, their interpretability is critically limited due to the enormous complexity. In this study, we present a method to make a…

Magnetic fields in large scale structure filaments beyond galaxy clusters remain poorly understood. Superclusters offer a unique setting to study these low density environments, where weak signals make detection challenging. The Faraday…

Wide-band radio polarization observations offer the possibility to recover information about the magnetic fields in synchrotron sources, such as details of their three-dimensional configuration, that has previously been inaccessible. The…

Combining principles with pragmatism, a new approach and accompanying algorithm are presented to a longstanding problem in applied statistics: the interpretation of principal components. Following Rousson and Gasser [53 (2004) 539--555]…

In Machine Learning, the $\mathsf{SHAP}$-score is a version of the Shapley value that is used to explain the result of a learned model on a specific entity by assigning a score to every feature. While in general computing Shapley values is…

In spite of several claims stating that some models are more interpretable than others -- e.g., "linear models are more interpretable than deep neural networks" -- we still lack a principled notion of interpretability to formally compare…

With the advent of highly predictive but opaque deep learning models, it has become more important than ever to understand and explain the predictions of such models. Existing approaches define interpretability as the inverse of complexity…

Machine learning algorithms often assume that training samples are independent. When data points are connected by a network, the induced dependency between samples is both a challenge, reducing effective sample size, and an opportunity to…

A number of visual quality measures have been introduced in visual analytics literature in order to automatically select the best views of high dimensional data from a large number of candidate data projections. These methods generally…

We present broadband polarimetric observations of a sample of high Faraday rotation measure (RM) AGN using the VLA telescope from 1 to 2 GHz, and 4 to 12 GHz. The sample (14 sources) consists of compact sources (linear resolution smaller…

A Faraday rotation measure (RM) catalogue, or RM Grid, is a valuable resource for the study of cosmic magnetism. Using the second data release (DR2) from the LOFAR Two-metre Sky Survey (LoTSS), we have produced a catalogue of 2461…

Hypersphere classification is a classical and foundational method that can provide easy-to-process explanations for the classification of real-valued and binary data. However, obtaining an (ideally concise) explanation via hypersphere…

Radio synchrotron emission, its polarization and its Faraday rotation are powerful tools to study the strength and structure of interstellar magnetic fields. The total intensity traces the strength and distribution of total magnetic fields.…

Interpretable Machine Learning (IML) is expected to remove significant barriers for the application of Machine Learning (ML) algorithms in power systems. This letter first seeks to showcase the benefits of SHapley Additive exPlanations…

Models often need to be constrained to a certain size for them to be considered interpretable. For example, a decision tree of depth 5 is much easier to understand than one of depth 50. Limiting model size, however, often reduces accuracy.…