Related papers: Explainable Galaxy Interaction Prediction with Hyb…
We compare predictions for galaxy-galaxy lensing profiles and clustering from the Henriques et al. (2015) public version of the Munich semi-analytical model of galaxy formation (SAM) and the IllustrisTNG suite, primarily TNG300, with…
Medical image annotation is essential for diagnosing diseases, yet manual annotation is time-consuming, costly, and prone to variability among experts. To address these challenges, we propose an automated explainable annotation system that…
We study the usage of EfficientNets and their applications to Galaxy Morphology Classification. We explore the usage of EfficientNets into predicting the vote fractions of the 79,975 testing images from the Galaxy Zoo 2 challenge on Kaggle.…
The combination of galaxy-galaxy lensing (GGL) and galaxy clustering is a powerful probe of low redshift matter clustering, especially if it is extended to the non-linear regime. To this end, we extend the N-body and halo occupation…
Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent neurodevelopmental disorder whose neuroimaging-based diagnosis remains challenging due to complex time-varying disruptions in brain connectivity. Functional MRI (fMRI) provides…
Galaxy formation theories predict that galaxy shapes and angular momenta have non-random alignments with the cosmic web. This leads to so-called intrinsic alignment between pairs of galaxies, which is important to quantify as a nuisance…
Graph Neural Networks (GNNs) excel at relational reasoning but face two persistent challenges: the lack of interpretable attribution for heterogeneous node types, and the computational overhead of message passing over large, noisy graphs.…
A physical understanding of galaxy formation and evolution benefits from an understanding of the connections between galaxies, their host dark matter halos, and their environments. In particular, interactions with more-massive neighbors can…
We employ several galaxy formation models, in particular, L-GALAXIES, IllustrisTNG, and EAGLE, as well as observational samples from SDSS and DESI, to investigate galactic conformity, the observed large-scale correlation between the…
Despite the success of convolution- and attention-based models in vision tasks, their rigid receptive fields and complex architectures limit their ability to model irregular spatial patterns and hinder interpretability, therefore posing…
The universe is composed of galaxies that have diverse shapes. Once the structure of a galaxy is determined, it is possible to obtain important information about its formation and evolution. Morphologically classifying galaxies means…
In this paper, we present a novel framework for enhancing model interpretability by integrating heatmaps produced separately by ResNet and a restructured 2D Transformer with globally weighted input saliency. We address the critical problem…
Large language models (LLMs) achieve strong average performance yet remain unreliable at the instance level, with frequent hallucinations, brittle failures, and poorly calibrated confidence. We study reliability through the lens of…
Transformer-based models have unlocked a plethora of powerful intelligent applications at the edge, such as voice assistant in smart home. Traditional deployment approaches offload the inference workloads to the remote cloud server, which…
Classification of spectra (1) and anomaly detection (2) are fundamental steps to guarantee the highest accuracy in redshift measurements (3) in modern all-sky spectroscopic surveys. We introduce a new Galaxy Spectra Neural Network…
We train three convolutional neural networks (CNNs) to classify galaxies with Galaxy Zoo 2 dataset and extract the activations from the last fully connected layer or the last average pooling layer of CNNs to study the high-dimensional…
Explainability of AI models is an important topic that can have a significant impact in all domains and applications from autonomous driving to healthcare. The existing approaches to explainable AI (XAI) are mainly limited to simple machine…
We use numerical simulations to investigate, for the first time, the joint effect of feedback from supernovae (SNe) and active galactic nuclei (AGN) on the evolution of galaxy cluster X-ray scaling relations. Our simulations are drawn from…
Convolutional Neural Networks (CNN) are more suitable, indeed. However, fixed kernel sizes make traditional CNN too specific, neither flexible nor conducive to feature learning, thus impacting on the classification accuracy. The convolution…
Real-time object detection in AR/VR systems faces critical computational constraints, requiring sub-10\,ms latency within tight power budgets. Inspired by biological foveal vision, we propose a two-stage pipeline that combines…