Related papers: Interpretable Faraday Complexity Classification
We present a detailed depolarization analysis of the radio galaxy \texttt{ILTJ012215.21+254334.8} using polarimetric data from the \textit{LOFAR Two-metre Sky Survey} (LoTSS) Data Release 2 (DR2) catalogue. This source, with \textit{RM}…
Magnetic fields play an important role in plasma dynamics, yet it is a quantity difficult to measure accurately with physical probes, whose presence disturbs the very field they measure. The Faraday rotation of a polarized beam of light…
Data complexity is an important concept in the natural sciences and related areas, but lacks a rigorous and computable definition. In this paper, we focus on a particular sense of complexity that is high if the data is structured in a way…
Plant species identification is time consuming, costly, and requires lots of efforts, and expertise knowledge. In recent, many researchers use deep learning methods to classify plants directly using plant images. While deep learning models…
This work presents a new classifier that is specifically designed to be fully interpretable. This technique determines the probability of a class outcome, based directly on probability assignments measured from the training data. The…
Interpretation of deep learning models is a very challenging problem because of their large number of parameters, complex connections between nodes, and unintelligible feature representations. Despite this, many view interpretability as a…
The nature of concept learning is a core question in cognitive science. Theories must account for the relative difficulty of acquiring different concepts by supervised learners. For a canonical set of six category types, two distinct…
The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on…
We analyze the trade-off between model complexity and accuracy for random forests by breaking the trees up into individual classification rules and selecting a subset of them. We show experimentally that already a few rules are sufficient…
(abridged) We run a Faraday structure determination data challenge to benchmark the currently available algorithms including Faraday synthesis (previously called RM synthesis in the literature), wavelet, compressive sampling and…
Data-driven models are central to scientific discovery. In efforts to achieve state-of-the-art model accuracy, researchers are employing increasingly complex machine learning algorithms that often outperform simple regressions in…
We describe how the observed polarization properties of an astronomical object are related to its intrinsic polarization properties and the finite temporal and spectral resolutions of the observing device. Moreover, we discuss the effect…
We present a numerical approach to investigate the relationship between magnetic fields and Faraday rotation effects in clusters of galaxies. We can infer the structure and strength of intra-cluster magnetic fields by comparing our…
Radio galaxies are linearly polarized -- an important property that allows us to infer the properties of the magnetic field of the source and its environment. However at low frequencies, Faraday rotation substantially depolarizes the…
We present an analysis of the polarization of compact radio sources from six pointings of the Westerbork Synthesis Radio Telescope (WSRT) at 350 MHz with 35% coverage in lambda^2. After correcting for the off-axis instrumental polarization…
Modern radio spectrometers make measurement of polarized intensity as a function of Faraday depth possible. I investigate the effect of depolarization along a model line of sight. I model sightlines with two components informed by…
Existing work on understanding deep learning often employs measures that compress all data-dependent information into a few numbers. In this work, we adopt a perspective based on the role of individual examples. We introduce a measure of…
Faraday rotation contains information about the magnetic field structure along the line of sight and is an important instrument in the study of cosmic magnetism. Traditional Faraday spectrum deconvolution methods such as RMCLEAN face…
Interpretation of a machine learning induced models is critical for feature engineering, debugging, and, arguably, compliance. Yet, best of breed machine learning models tend to be very complex. This paper presents a method for model…
In order for machine learning to be deployed and trusted in many applications, it is crucial to be able to reliably explain why the machine learning algorithm makes certain predictions. For example, if an algorithm classifies a given…