相关论文: A Probabilistic Autoencoder for Type Ia Supernovae…

Variational Autoencoders (VAEs) are a popular framework for unsupervised learning and data generation. A plethora of methods have been proposed focusing on improving VAEs, with the incorporation of adversarial objectives and the integration…

This study introduces a compositional autoencoder (CAE) framework designed to disentangle the complex interplay between genotypic and environmental factors in high-dimensional phenotype data to improve trait prediction in plant breeding and…

In the next decade Type Ia supernovae (SNe Ia) will be used to test theories predicting changes in the Dark Energy equation of state with time. Ultimately this requires a dedicated space mission like JDEM. SNe Ia are mature cosmological…

Variational Autoencoders (VAEs), as a form of deep generative model, have been widely used in recent years, and shown great great peformance in a number of different domains, including image generation and anomaly detection, etc.. This…

In recent years, the popularity of fingerprint-based biometric authentication systems significantly increased. However, together with many advantages, biometric systems are still vulnerable to presentation attacks (PAs). In particular, this…

Is there really much more to say about sparse autoencoders (SAEs)? Autoencoders in general, and SAEs in particular, represent deep architectures that are capable of modeling low-dimensional latent structure in data. Such structure could…

In the era of large astronomical surveys, photometric classification of supernovae (SNe) has become an important research field due to limited spectroscopic resources for candidate follow-up and classification. In this work, we present a…

Type Ia supernovae (SNae Ia), standardisable candles that allow tracing the expansion history of the Universe, are instrumental in constraining cosmological parameters, particularly dark energy. State-of-the-art likelihood-based analyses…

Accounting for selection effects in supernova type Ia (SN Ia) cosmology is crucial for unbiased cosmological parameter inference -- even more so for the next generation of large, mostly photometric-only surveys. The conventional "bias…

We show how spectra of Type Ia supernovae (SNe Ia) at maximum light can be used to improve cosmological distance estimates. In a companion article, we used manifold learning to build a three-dimensional parameterization of the intrinsic…

Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of…

Estimation of uncertainty in deep learning models is of vital importance, especially in medical imaging, where reliance on inference without taking into account uncertainty could lead to misdiagnosis. Recently, the probabilistic Variational…

In this paper, we suggest a framework to make use of mutual information as a regularization criterion to train Auto-Encoders (AEs). In the proposed framework, AEs are regularized by minimization of the mutual information between input and…

In this second paper in a series we present measurements of spectral features of 432 low-redshift (z < 0.1) optical spectra of 261 Type Ia supernovae (SNe Ia) within 20 d of maximum brightness. The data were obtained from 1989 through the…

While unsupervised variational autoencoders (VAE) have become a powerful tool in neuroimage analysis, their application to supervised learning is under-explored. We aim to close this gap by proposing a unified probabilistic model for…

We present a data-driven method based on long short-term memory (LSTM) neural networks to analyze spectral time series of Type Ia supernovae (SNe Ia). The dataset includes 3091 spectra from 361 individual SNe Ia. The method allows for…

Neural Networks play a growing role in many science disciplines, including physics. Variational Autoencoders (VAEs) are neural networks that are able to represent the essential information of a high dimensional data set in a low dimensional…

The variational autoencoder (VAE) is a popular probabilistic generative model. However, one shortcoming of VAEs is that the latent variables cannot be discrete, which makes it difficult to generate data from different modes of a…

Does a Variational AutoEncoder (VAE) consistently encode typical samples generated from its decoder? This paper shows that the perhaps surprising answer to this question is `No'; a (nominally trained) VAE does not necessarily amortize…

Unsupervised anomaly detection is a challenging task. Autoencoders (AEs) or generative models are often employed to model the data distribution of normal inputs and subsequently identify anomalous, out-of-distribution inputs by high…