Related papers: Interpretable machine learning for finding interme…
High-throughput technologies such as next generation sequencing allow biologists to observe cell function with unprecedented resolution, but the resulting datasets are too large and complicated for humans to understand without the aid of…
Recent efforts in Machine Learning (ML) interpretability have focused on creating methods for explaining black-box ML models. However, these methods rely on the assumption that simple approximations, such as linear models or decision-trees,…
With the spread and rapid advancement of black box machine learning models, the field of interpretable machine learning (IML) or explainable artificial intelligence (XAI) has become increasingly important over the last decade. This is…
Globular clusters (GCs) are thought to harbor the long-sought population of intermediate-mass black holes (IMBHs). We present a systematic search for a putative IMBH in 81 Milky Way GCs, based on archival Chandra X-ray observations. We find…
Prediction of survival in patients diagnosed with a brain tumour is challenging because of heterogeneous tumour behaviours and responses to treatment. Better estimations of prognosis would support treatment planning and patient support.…
Intermediate-mass black holes (IMBHs) by definition have masses of $M_{\rm IMBH} \sim 10^{2-5}~M_\odot$, a range with few observational constraints. Finding IMBHs in globular star clusters (GCs) would validate a formation channel for…
Globular clusters (GCs) have been at the heart of many longstanding questions in many sub-fields of astronomy and, as such, systematic identification of GCs in external galaxies has immense impacts. In this study, we take advantage of M87's…
There have been reports of possible detections of intermediate-mass black holes (IMBHs) in globular clusters (GCs). Empirically, there exists a tight correlation between the central supermassive black hole (SMBH) mass and the mean velocity…
The existence of intermediate-mass black holes (IMBHs) in globular clusters (GCs) remains a crucial problem. Searching IMBHs in GCs reveals a discrepancy between radio observations and dynamical modelings: the upper mass limits constrained…
By means of a multimass isotropic and spherical model that includes the self-consistent treatment of a central intermediate-mass black hole (IMBH), the influence of this black hole on the morphological and physical properties of globular…
To learn about real world phenomena, scientists have traditionally used models with clearly interpretable elements. However, modern machine learning (ML) models, while powerful predictors, lack this direct elementwise interpretability (e.g.…
We discuss the potential of the gravitational microlensing method as a unique tool to detect unambiguous signals caused by intermediate-mass black holes in globular clusters. We select clusters near the line of sight to the Galactic Bulge…
Deep learning approaches have recently been extensively explored for the prognostics of industrial assets. However, they still suffer from a lack of interpretability, which hinders their adoption in safety-critical applications. To improve…
In this paper we explore the interplay between intermediate-mass black holes (IMBHs) and their nursing globular clusters (GCs), taking advantage of over 2000 Monte Carlo GC models. We find that the average density of IMBHs sphere of…
In machine learning (ML), it is in general challenging to provide a detailed explanation on how a trained model arrives at its prediction. Thus, usually we are left with a black-box, which from a scientific standpoint is not satisfactory.…
In this work, we address the following question: ``can we use the current cosmological simulations to identify intermediate-mass black holes (IMBHs) and quantify a putative population of wandering IMBHs?''. We compare wandering-IMBH counts…
Interpretable machine learning (IML) becomes increasingly important in highly regulated industry sectors related to the health and safety or fundamental rights of human beings. In general, the inherently IML models should be adopted because…
Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions, and in more intuitive user…
It has been assumed that intermediate-mass black holes (IMBHs) in globular clusters can only reside in the most centrally concentrated clusters, with a so-called `core-collapsed' density profile. While this would be a natural guess, it is…
Objectives: We study interpretable recidivism prediction using machine learning (ML) models and analyze performance in terms of prediction ability, sparsity, and fairness. Unlike previous works, this study trains interpretable models that…