AstroML Journal Club

Home
Communication
AstroML Journal Club

The AstroML journal club, held every Tuesday, is an initiative within the TITAN project aimed at fostering scientific exchange between computer scientists and astrophysicists in our group. Our goal is to facilitate weekly discussions on one or two papers focusing on machine/deep learning methods applied to astrophysics and cosmology. By doing so, we aim to initiate dialogue across both fields and ensure that state-of-the-art scientific advancements are accessible and understood by all members.

GAIN: Missing Data Imputation using Generative Adversarial Nets

Speaker : Anastasia Aidini (Postdoctoral Research)
Date : 16th of April
Location: FORTH
Paper Abstract: We propose a novel method for imputing missing data by adapting the well-known Generative Ad- versarial Net...

Missing Data Imputation for Galaxy Redshift Estimation

Speaker : Anastasia Aidini (Postdoctoral Research)
Date : 16th of April
Location: FORTH
Paper Abstract: Astronomical data is full of holes. While there are many reasons for this missing data, the data can be randomly...

Inpainting Galactic Foreground Intensity and Polarization maps using Convolutional Neural Network

Speaker : Kostas Zafeirakis (undergrad student)
Date : 2nd of April
Location: FORTH
Paper Abstract: Deep convolutional neural networks have been a popular tool for image generation and restoration. The performance of thes...

Can Diffusion Model Conditionally Generate Astrophysical Images?

Speaker : Andreas Tersenov (PhD student)
Date : 19th of March
Location: FORTH
Paper Abstract: Generative adversarial networks (GANs) are frequently utilized in astronomy to construct an emulator of numerical simulations. ...

Deep learning for intensity mapping observations: Component extraction

Speaker : Athanasia Gkogkou (Postdoctoral researcher)
Date : 12th of March
Location: FORTH
Paper Abstract: Line intensity mapping (LIM) is an emerging observational method to study the large- scale structure of the Univ...

Conformal Prediction, A Gentle Introduction

Speaker : Konidakis Ioannis (MScstudent)
Date : 5th of March
Location: FORTH
Paper Abstract: Black-box machine learning models are now routinely used in high-risk settings, like medical diagnostics, which demand uncertainty q...

AstroML Journal Club

GAIN: Missing Data Imputation using Generative Adversarial Nets

Missing Data Imputation for Galaxy Redshift Estimation

Inpainting Galactic Foreground Intensity and Polarization maps using Convolutional Neural Network

Can Diffusion Model Conditionally Generate Astrophysical Images?

Deep learning for intensity mapping observations: Component extraction

Conformal Prediction, A Gentle Introduction

Project

Products

Contact ERA Chair

Contact Project Coordinator