Related papers: Unsupervised Domain Adaptation for Constraining St…
The use of machine learning is becoming ubiquitous in astronomy, but remains rare in the study of the atmospheres of exoplanets. Given the spectrum of an exoplanetary atmosphere, a multi-parameter space is swept through in real time to find…
In order to reproduce the low mass end of the stellar mass function, most current models of galaxy evolution invoke very efficient supernova feedback. This solution seems to suffer from several shortcomings however, like predicting too…
Understanding human visual attention is key to preserving cultural heritage We introduce SPGen a novel deep learning model to predict scanpaths the sequence of eye movementswhen viewers observe paintings. Our architecture uses a Fully…
All famous machine learning algorithms that comprise both supervised and semi-supervised learning work well only under a common assumption: the training and test data follow the same distribution. When the distribution changes, most…
Despite the importance of quantifying how the spatial patterns of extreme precipitation will change with warming, we lack tools to objectively analyze the storm-scale outputs of modern climate models. To address this gap, we develop an…
Modern data empower observers to describe galaxies as the spatially and biographically complex objects they are. We illustrate this through case studies of four, $z\sim1.3$ systems based on deep, spatially resolved, 17-band + G102 + G141…
The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an unlabeled target domain, with a similar but different data distribution. Most deep learning approaches to…
One of the main themes in extragalactic astronomy for the next decade will be the evolution of galaxies over cosmic time. Many future observatories, including JWST, ALMA, GMT, TMT and E-ELT will intensively observe starlight over a broad…
Galaxy observations are influenced by many physical parameters: stellar masses, star formation rates (SFRs), star formation histories (SFHs), metallicities, dust, black hole activity, and more. As a result, inferring accurate physical…
It has been argued that the specific star formation rates of star forming galaxies inferred from observational data decline more rapidly below z = 2 than is predicted by hierarchical galaxy formation models. We present a detailed analysis…
Unsupervised domain adaptation aiming to learn a specific task for one domain using another domain data has emerged to address the labeling issue in supervised learning, especially because it is difficult to obtain massive amounts of…
Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, subspace-based methods form an important class of solutions to this problem. Despite their…
With the advent of several galaxy surveys targeting star-forming galaxies, it is important to have models capable of interpreting their spatial distribution in terms of astrophysical and cosmological parameters. To address this need, we…
The assumption that training and testing samples are generated from the same distribution does not always hold for real-world machine-learning applications. The procedure of tackling this discrepancy between the training (source) and…
Real-world time-series datasets often violate the assumptions of standard supervised learning for forecasting -- their distributions evolve over time, rendering the conventional training and model selection procedures suboptimal. In this…
This review summarizes popular unsupervised learning methods, and gives an overview of their past, current, and future uses in astronomy. Unsupervised learning aims to organise the information content of a dataset, in such a way that…
The combination of huge databases of galaxy spectra and advances in evolutionary synthesis models in the past few years has renewed interest in an old question: How to estimate the star formation history of a galaxy out of its integrated…
In the context of supervised statistical learning, it is typically assumed that the training set comes from the same distribution that draws the test samples. When this is not the case, the behavior of the learned model is unpredictable and…
Context. Generative models open up the possibility to interrogate scientific data in a more data-driven way. Aims: We propose a method that uses generative models to explore hypotheses in astrophysics and other areas. We use a neural…
The spectral energy distribution of a galaxy emerges from the complex interplay of many physical ingredients, including its star formation history (SFH), metallicity evolution, and dust properties. Using GALAXPY, a new galaxy spectral…