Related papers: A Probabilistic Autoencoder for Type Ia Supernovae…

This paper presents a novel convolutional neural network (CNN) based image compression framework via scalable auto-encoder (SAE). Specifically, our SAE based deep image codec consists of hierarchical coding layers, each of which is an…

Early polarization observations on Type Ia supernovae (SNe Ia) may reveal the geometry of supernova ejecta, and then put constraints on their explosion mechanism and their progenitor model. We performed a literature search of SNe Ia with…

Variational autoencoders (VAEs) provide an effective and simple method for modeling complex distributions. However, training VAEs often requires considerable hyperparameter tuning to determine the optimal amount of information retained by…

Sequence data is challenging for machine learning approaches, because the lengths of the sequences may vary between samples. In this paper, we present an unsupervised learning model for sequence data, called the Integrated Sequence…

In this tutorial, we explore Variational Autoencoders (VAEs), an essential framework for unsupervised learning, particularly suited for high-dimensional datasets such as neuroimaging. By integrating deep learning with Bayesian inference,…

The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference. It typically makes strong…

Autoencoders, as a dimensionality reduction technique, have been recently applied to outlier detection. However, neural networks are known to be vulnerable to overfitting, and therefore have limited potential in the unsupervised outlier…

Many real-world monitoring and surveillance applications require non-trivial anomaly detection to be run in the streaming model. We consider an incremental-learning approach, wherein a deep-autoencoding (DAE) model of what is normal is…

Deep latent variable models, trained using variational autoencoders or generative adversarial networks, are now a key technique for representation learning of continuous structures. However, applying similar methods to discrete structures,…

Stack autoencoder (SAE), as a representative deep network, has unique and excellent performance in feature learning, and has received extensive attention from researchers. However, existing deep SAEs focus on original samples without…

Masked AutoEncoders (MAE) have emerged as a robust self-supervised framework, offering remarkable performance across a wide range of downstream tasks. To increase the difficulty of the pretext task and learn richer visual representations,…

Due to the rare occurrence of anomalous events, a typical approach to anomaly detection is to train an autoencoder (AE) with normal data only so that it learns the patterns or representations of the normal training data. At test time, the…

Autoencoders have been widely used for dimensional reduction and feature extraction. Various types of autoencoders have been proposed by introducing regularization terms. Most of these regularizations improve representation learning by…

In recent years, studies on image generation models of spiking neural networks (SNNs) have gained the attention of many researchers. Variational autoencoders (VAEs), as one of the most popular image generation models, have attracted a lot…

Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming to extract and analyze biologically meaningful features from…

We present a public, open-source relational database (we name kaepora) containing a sample of 4975 spectra of 777 Type Ia supernovae (SNe Ia). Since we draw from many sources, we significantly improve the spectra by inspecting these data…

Traditional cosmological inference using Type Ia supernovae (SNeIa) have used stretch- and color-corrected fits of SN Ia light curves and assumed a resulting fiducial mean and symmetric intrinsic dispersion for the resulting relative…

We propose a novel filter for sparse big data, called an integrated autoencoder (IAE), which utilizes auxiliary information to mitigate data sparsity. The proposed model achieves an appropriate balance between prediction accuracy,…

Accurate estimation of the relative concentrations of chromophores in a spectroscopic photoacoustic (sPA) image can reveal immense structural, functional, and molecular information about physiological processes. However, due to…

Electron, optical, and scanning probe microscopy methods are generating ever increasing volume of image data containing information on atomic and mesoscale structures and functionalities. This necessitates the development of the machine…