Related papers: Disentangled Representation Learning for Astronomi…
We report an interpretation method for deep learning models that allows us to handle high-dimensional spectral data in materials science. The proposed method uses feature extraction and clustering analysis to categorize materials into…
The Sun has been found to be depleted in refractory (rock-forming) elements relative to nearby solar analogs, suggesting a potential indicator of planet formation. Given the small amplitude of the depletion, previous analyses have primarily…
Deep learning with artificial neural networks is increasingly gaining attention, because of its potential for data-driven astronomy. However, this methodology usually does not provide uncertainties and does not deal with incompleteness and…
Chemical tagging promises to use detailed abundance measurements to identify spatially separated stars that were in fact born together (in the same molecular cloud), long ago. This idea has not yielded much practical success, presumably…
This paper presents a novel approach that leverages domain variability to learn representations that are conditionally invariant to unwanted variability or distractors. Our approach identifies both spurious and invariant latent features…
Recent theoretical calculations of stellar evolutionary tracks for rotating high-mass stars suggests that the chemical composition of the surface layers changes even whilst the star is evolving on the Main Sequence. The abundance analysis…
Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…
Disentangled representations seek to recover latent factors of variation underlying observed data, yet their identifiability is still not fully understood. We introduce a unified framework in which disentanglement is achieved through…
In the last two decades about a dozen methods were invented which derive, from a series of composite spectra over the orbit, the spectra of individual components in binary and multiple systems. Reconstructed spectra can then be analyzed…
Representation learning is the foundation for the recent success of neural network models. However, the distributed representations generated by neural networks are far from ideal. Due to their highly entangled nature, they are di cult to…
Disentangled representations, where the higher level data generative factors are reflected in disjoint latent dimensions, offer several benefits such as ease of deriving invariant representations, transferability to other tasks,…
Chemical tagging is a central pursuit of galactic archaeology, but requires sufficiently discriminative abundances to uniquely identify sites of star formation. This task is complicated by intrinsic scatter among conatal stars,…
Humans have a remarkable ability to disentangle complex sensory inputs (e.g., image, text) into simple factors of variation (e.g., shape, color) without much supervision. This ability has inspired many works that attempt to solve the…
Upcoming million-star spectroscopic surveys have the potential to revolutionize our view of the formation and chemical evolution of the Milky Way. Realizing this potential requires automated approaches to optimize estimates of stellar…
Disentangled representation learning aims to uncover latent variables underlying the observed data, and generally speaking, rather strong assumptions are needed to ensure identifiability. Some approaches rely on sufficient changes on the…
We have shown that data-driven models are effective for inferring physical attributes of stars (labels; Teff, logg, [M/H]) from spectra, even when the signal-to-noise ratio is low. Here we explore whether this is possible when the…
It is now well-established that the elemental abundance patterns of stars holds key clues not only to their formation but also to the assembly histories of galaxies. One of the most exciting possibilities is the use of stellar abundance…
High-precision spectroscopy of large stellar samples plays a crucial role for several topical issues in astrophysics. Examples include studying the chemical structure and evolution of the Milky Way galaxy, tracing the origin of chemical…
One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequence of dynamic factors. To extract this latent information,…
Learning disentangled representations of data is a fundamental problem in artificial intelligence. Specifically, disentangled latent representations allow generative models to control and compose the disentangled factors in the synthesis…