Related papers: Interpreting automatic AGN classifiers with salien…

While success of Deep Learning (DL) in automated diagnosis can be transformative to the medicinal practice especially for people with little or no access to doctors, its widespread acceptability is severely limited by inherent black-box…

We present a new method to predict the line-of-sight column density (NH) values of active galactic nuclei (AGN) based on mid-infrared (MIR), soft, and hard X-ray data. We developed a multiple linear regression machine learning algorithm…

We present a composite machine learning framework to estimate posterior probability distributions of bulge-to-total light ratio, half-light radius, and flux for Active Galactic Nucleus (AGN) host galaxies within $z<1.4$ and $m<23$ in the…

In this work we develop a fast saliency detection method that can be applied to any differentiable image classifier. We train a masking model to manipulate the scores of the classifier by masking salient parts of the input image. Our model…

Accurate active galactic nucleus (AGN) identifications in large galaxy samples are crucial to assess the role of AGN and AGN feedback in the coevolution of galaxies and their central supermassive black holes. Emission line flux ratio…

Developments in machine learning interpretability techniques over the past decade have provided new tools to observe the image regions that are most informative for classification and localization in artificial neural networks (ANNs). Are…

Anomaly detection is a task that recognizes whether an input sample is included in the distribution of a target normal class or an anomaly class. Conventional generative adversarial network (GAN)-based methods utilize an entire image…

It is known that deep neural networks (DNNs) classify an input image by paying particular attention to certain specific pixels; a graphical representation of the magnitude of attention to each pixel is called a saliency-map. Saliency-maps…

Automatic source detection and classification tools based on machine learning (ML) algorithms are growing in popularity due to their efficiency when dealing with large amounts of data simultaneously and their ability to work in…

To understand the cosmic accretion history of supermassive black holes, separating the radiation from active galactic nuclei (AGNs) and star-forming galaxies (SFGs) is critical. However, a reliable solution on photometrically recognising…

While machine learning techniques have been successfully applied in several fields, the black-box nature of the models presents challenges for interpreting and explaining the results. We develop a new framework called Adaptive Explainable…

We investigate the influence of adversarial training on the interpretability of convolutional neural networks (CNNs), specifically applied to diagnosing skin cancer. We show that gradient-based saliency maps of adversarially trained CNNs…

Deep learning methods based on Convolutional Neural Networks (CNNs) have shown great potential to improve early and accurate diagnosis of Alzheimer's disease (AD) dementia based on imaging data. However, these methods have yet to be widely…

Gradient-based saliency maps are widely used to explain deep neural network decisions. However, as models become deeper and more black-box, such as in closed-source APIs like ChatGPT, computing gradients become challenging, hindering…

While emission-line flux ratio diagnostics are the most common technique for identifying active galactic nuclei (AGNs) in optical spectra, applying this approach to single fiber spectra of galaxies can omit entire subpopulations of AGNs.…

In recent years, neural networks have continued to flourish, achieving high efficiency in detecting relevant objects in photos or simply recognizing (classifying) these objects - mainly using CNN networks. Current solutions, however, are…

We argue that interpretations of machine learning (ML) models or the model-building process can be seen as a form of sensitivity analysis (SA), a general methodology used to explain complex systems in many fields such as environmental…

Active Galactic Nuclei (AGN) are believed to be powered by accretion of matter onto a supermassive black hole. A fundamental ingredient in shaping our understanding of AGN is their variability across the entire electromagnetic spectrum.…

Though deep learning techniques have made great progress in salient object detection recently, the predicted saliency maps still suffer from incomplete predictions due to the internal complexity of objects and inaccurate boundaries caused…

Deep neural networks (DNNs) have made significant strides in Natural Language Processing (NLP), yet their interpretability remains elusive, particularly when evaluating their intricate decision-making processes. Traditional methods often…