Related papers: Interpretable machine learning for finding interme…
The formation of supermassive black holes at high redshift still remains a puzzle to astronomers. Their growth becomes reasonable only when starting from a massive seed black hole with mass of the order of 10^2 - 10^5 M_SUN.…
Empirical evidence for both stellar mass black holes M_bh<10^2 M_sun) and supermassive black holes (SMBHs, M_bh>10^5 M_sun) is well established. Moreover, every galaxy with a bulge appears to host a SMBH, whose mass is correlated with the…
Automated Machine Learning-based systems' integration into a wide range of tasks has expanded as a result of their performance and speed. Although there are numerous advantages to employing ML-based systems, if they are not interpretable,…
This paper examines two different yet related questions related to explainable AI (XAI) practices. Machine learning (ML) is increasingly important in financial services, such as pre-approval, credit underwriting, investments, and various…
Recently, an intermediate-mass black hole (IMBH) candidate was announced in the Galactic globular cluster Omega Centauri. IMBHs at the lower end of the traditional mass range have also been detected through gravitational-wave transients,…
Energy based models (EBMs) are appealing due to their generality and simplicity in likelihood modeling, but have been traditionally difficult to train. We present techniques to scale MCMC based EBM training on continuous neural networks,…
Methods for interpreting machine learning black-box models increase the outcomes' transparency and in turn generates insight into the reliability and fairness of the algorithms. However, the interpretations themselves could contain…
Digital mammography is essential to breast cancer detection, and deep learning offers promising tools for faster and more accurate mammogram analysis. In radiology and other high-stakes environments, uninterpretable ("black box") deep…
Despite increasing interest in the field of Interpretable Machine Learning (IML), a significant gap persists between the technical objectives targeted by researchers' methods and the high-level goals of consumers' use cases. In this work,…
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…
Intermediate-mass black holes (IMBHs) may provide the missing link to understanding the growth of supermassive black holes in the early Universe. Some formation scenarios predict that IMBHs could have formed by runaway collisions in…
We investigate the evolution of star clusters containing intermediate-mass black hole (IMBH) of $300$ to $5000\ \mathrm{M}_\odot$, focusing on the formation and evolution of IMBH-stellar mass black holes (SBHs; $M_{\rm BH} \lesssim 10^2\…
Machine learning is permeating every conceivable domain to promote data-driven decision support. The focus is often on advanced black-box models due to their assumed performance advantages, whereas interpretable models are often associated…
This study explores the explainability capabilities of large language models (LLMs), when employed to autonomously generate machine learning (ML) solutions. We examine two classification tasks: (i) a binary classification problem focused on…
Many risk-sensitive applications require Machine Learning (ML) models to be interpretable. Attempts to obtain interpretable models typically rely on tuning, by trial-and-error, hyper-parameters of model complexity that are only loosely…
Spectroscopic and photometric observations show that many globular clusters host multiple stellar populations, challenging the common paradigm that globular clusters are "simple stellar populations" composed of stars of uniform age and…
Machine learning is a vital part of many real-world systems, but several concerns remain about the lack of interpretability, explainability and robustness of black-box AI systems. Concept Bottleneck Models (CBM) address some of these…
Regional climate models (RCMs) are essential tools for simulating and studying regional climate variability and change. However, their high computational cost limits the production of comprehensive ensembles of regional climate projections…
Extreme weather variations and the increasing unpredictability of load behavior make it difficult to determine power grid dispatches that are robust to uncertainties. While machine learning (ML) methods have improved the ability to model…
Polymers, integral to advancements in high-tech fields, necessitate the study of their thermal conductivity (TC) to enhance material attributes and energy efficiency. The TC of polymers obtained by molecular dynamics (MD) calculations and…