Related papers: Enhancing Cosmological Model Selection with Interp…

Spacecraft operations are highly critical, demanding impeccable reliability and safety. Ensuring the optimal performance of a spacecraft requires the early detection and mitigation of anomalies, which could otherwise result in unit or…

We employ Bayesian Model Averaging (BMA) as a powerful statistical framework to address key cosmological questions about the universe's fundamental properties. We explore extensions beyond the standard $\Lambda$CDM model, considering a…

The existence of 'peculiar' velocities due to the formation of cosmic structure marks a point of discord between the real Universe and the usually assumed Friedmann-Lema\'{i}tre-Robertson-Walker metric which accomodates only the smooth…

The design of interpretable deep learning models working in relational domains poses an open challenge: interpretable deep learning methods, such as Concept Bottleneck Models (CBMs), are not designed to solve relational problems, while…

The $\Lambda$CDM model has long served as the cornerstone of modern cosmology, offering an elegant and successful framework for interpreting a wide range of cosmological observations. However, the rise of high-precision datasets has…

Modelling the mass distributions of strong gravitational lenses is often necessary to use them as astrophysical and cosmological probes. With the high number of lens systems ($>10^5$) expected from upcoming surveys, it is timely to explore…

Over the past decade advancements in the understanding of several astrophysical phenomena have allowed us to infer a concordance cosmological model that successfully accounts for most of the observations of our universe. This has opened up…

The success of present and future cosmological studies is tied to the ability to detect discrepancies in complex data sets within the framework of a cosmological model. Tensions caused by the presence of unknown systematic effects need to…

Quantum machine learning (QML) is making rapid progress, and QML-based models hold the promise of quantum advantages such as potentially higher expressivity and generalizability than their classical counterparts. Here, we present work on…

We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure…

Interpretability in machine learning models is important in high-stakes decisions, such as whether to order a biopsy based on a mammographic exam. Mammography poses important challenges that are not present in other computer vision tasks:…

Deep Neural Networks use thousands of mostly incomprehensible features to identify a single class, a decision no human can follow. We propose an interpretable sparse and low dimensional final decision layer in a deep neural network with…

Machine-learning based classifiers have become indispensable in the field of astrophysics, allowing separation of astronomical sources into various classes, with computational efficiency suitable for application to the enormous data volumes…

Distinguishing galaxies as either fast or slow rotators plays a vital role in understanding the processes behind galaxy formation and evolution. Standard techniques, which are based on the $\lambda_R$-spin parameter obtained from stellar…

Nowadays, neural network (NN) and deep learning (DL) techniques are widely adopted in many applications, including recommender systems. Given the sparse and stochastic nature of collaborative filtering (CF) data, recent works have…

We report constraints on a variety of non-standard cosmological models using the full 5-year photometrically-classified type Ia supernova sample from the Dark Energy Survey (DES-SN5YR). Both Akaike Information Criterion (AIC) and…

Deep reinforcement learning has been extensively studied in decision-making processes and has demonstrated superior performance over conventional approaches in various fields, including radar resource management (RRM). However, a notable…

The generalization of machine learning (ML) models to out-of-distribution (OOD) examples remains a key challenge in extracting information from upcoming astronomical surveys. Interpretability approaches are a natural way to gain insights…

Network intrusion detection (NID) systems which leverage machine learning have been shown to have strong performance in practice when used to detect malicious network traffic. Decision trees in particular offer a strong balance between…

Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a…