Related papers: A Probabilistic Autoencoder for Type Ia Supernovae…
SNe Ia continue to play a key role in cosmological measurements. Their interpretation over a range in redshift requires a rest-frame spectral energy distribution model. For practicality, these models are parameterized with a limited number…
The remarkable uniformity of Type Ia supernovae (SNe Ia) has allowed astronomers to use them as distance indicators to measure the properties and expansion history of the Universe. However, SNe Ia exhibit intrinsic variation in both their…
Hyperspectral imagery provides rich spectral detail but poses unique challenges because of its high dimensionality in both spatial and spectral domains. We propose \textit{HyperspectralMAE}, a Transformer-based foundation model for…
This is the first release of optical spectroscopic data of low-redshift Type Ia supernovae (SNe Ia) by the Carnegie Supernova Project including 604 previously unpublished spectra of 93 SNe Ia. The observations cover a range of phases from…
Optimal computations under uncertainty require an adequate probabilistic representation about beliefs. Deep generative models, and specifically Variational Autoencoders (VAEs), have the potential to meet this demand by building latent…
Continuing advances in neural interfaces have enabled simultaneous monitoring of spiking activity from hundreds to thousands of neurons. To interpret these large-scale data, several methods have been proposed to infer latent dynamic…
The physics driving type Ia supernovae (SNe~Ia) standardisation in cosmology remains poorly-understood. Recent advances however mean that it is now possible to systematically analyse the explosion properties of large numbers of cosmological…
While the beta-VAE family is aiming to find disentangled representations and acquire human-interpretable generative factors, like what an ICA (from the linear domain) does, we propose Full Encoder, a novel unified autoencoder framework as a…
Type Ia Supernovae (SNe Ia) are widely used to measure the expansion of the Universe. Improving distance measurements of SNe Ia is one technique to better constrain the acceleration of expansion and determine its physical nature. This…
Following our previous study of Artificial Intelligence Assisted Inversion (AIAI) of supernova analyses (Chen et al. 2020), we train a set of deep neural networks based on the one-dimensional radiative transfer code TARDIS (Kerzendorf & Sim…
Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dimension. We argue that this discrepancy may contribute to the…
In recent years Variation Autoencoders have become one of the most popular unsupervised learning of complicated distributions.Variational Autoencoder (VAE) provides more efficient reconstructive performance over a traditional autoencoder.…
This study investigates the use of non-linear unsupervised dimensionality reduction techniques to compress a music dataset into a low-dimensional representation which can be used in turn for the synthesis of new sounds. We systematically…
Motivated by the fact that calibrated light curves of Type Ia supernovae (SNe Ia) have become a major tool to determine the expansion history of the Universe, considerable attention has been given to, both, observations and models of these…
Inference for Variational Autoencoders (VAEs) consists of learning two models: (1) a generative model, which transforms a simple distribution over a latent space into the distribution over observed data, and (2) an inference model, which…
Approximating distributions over complicated manifolds, such as natural images, are conceptually attractive. The deep latent variable model, trained using variational autoencoders and generative adversarial networks, is now a key technique…
The existence of multiple subclasses of type Ia supernovae (SNeIa) has been the subject of great debate in the last decade. One major challenge inevitably met when trying to infer the existence of one or more subclasses is the time…
Variational Autoencoders (VAEs) have experienced recent success as data-generating models by using simple architectures that do not require significant fine-tuning of hyperparameters. However, VAEs are known to suffer from…
A method is presented for automated photometric classification of supernovae (SNe) as Type-Ia or non-Ia. A two-step approach is adopted in which: (i) the SN lightcurve flux measurements in each observing filter are fitted separately; and…
We generate $\sim$ 100,000 model spectra of Type Ia Supernovae (SNIa) to form a spectral library for the purpose of building an Artificial Intelligence Assisted Inversion (AIAI) algorithm for theoretical models. As a first attempt, we…