English
Related papers

Related papers: Elf autoencoder: unsupervised exploration of flat-…

200 papers

A model for two-dimensional electronic, photonic, and mechanical metamaterial systems is presented, which has flat one-dimensional zero-mode energy bands and stable localized states of a topological origin confined within twin boundaries,…

Mesoscale and Nanoscale Physics · Physics 2019-02-06 Linghua Zhu , Emil Prodan , Keun Hyuk Ahn

Over the last two decades, Electron Energy Loss Spectroscopy (EELS) imaging with a scanning transmission electron microscope (STEM) has emerged as a technique of choice for visualizing complex chemical, electronic, plasmonic, and phononic…

The growth in the number of galaxy images is much faster than the speed at which these galaxies can be labelled by humans. However, by leveraging the information present in the ever growing set of unlabelled images, semi-supervised learning…

Machine Learning · Statistics 2020-11-18 Mizu Nishikawa-Toomey , Lewis Smith , Yarin Gal

Recent advances in the field of generative models and in particular generative adversarial networks (GANs) have lead to substantial progress for controlled image editing, especially compared with the pre-deep learning era. Despite their…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Gwilherm Lesné , Yann Gousseau , Saïd Ladjal , Alasdair Newson

Design of experiments (DOE) is playing an essential role in learning and improving a variety of objects and processes. The article discusses the application of unsupervised machine learning to support the pragmatic designs of complex…

Machine Learning · Computer Science 2021-10-07 Alex Glushkovsky

Automatic extraction of chemical structures from scientific literature plays a crucial role in accelerating research across fields ranging from drug discovery to materials science. Patent documents, in particular, contain molecular…

Computer Vision and Pattern Recognition · Computer Science 2025-10-09 Lucas Morin , Gerhard Ingmar Meijer , Valéry Weber , Luc Van Gool , Peter W. J. Staar

Physics-constrained data-driven computing is an emerging computational paradigm that allows simulation of complex materials directly based on material database and bypass the classical constitutive model construction. However, it remains…

Numerical Analysis · Mathematics 2022-09-12 Xiaolong He , Qizhi He , Jiun-Shyan Chen

Most of the existing literature regarding hyperbolic embedding concentrate upon supervised learning, whereas the use of unsupervised hyperbolic embedding is less well explored. In this paper, we analyze how unsupervised tasks can benefit…

Machine Learning · Computer Science 2021-03-31 Jiwoong Park , Junho Cho , Hyung Jin Chang , Jin Young Choi

We introduce physics-informed multimodal autoencoders (PIMA) - a variational inference framework for discovering shared information in multimodal scientific datasets representative of high-throughput testing. Individual modalities are…

Machine Learning · Computer Science 2022-02-08 Nathaniel Trask , Carianne Martinez , Kookjin Lee , Brad Boyce

Electronic bands near the Fermi energy with minimal energy dispersion in k-space, i.e. "flat bands", are often said to be an important characteristic of superconducting materials. When extending over a significant region of the k-space,…

Superconductivity · Physics 2020-07-16 Zoë S. Yang , Austin M. Ferrenti , Robert J. Cava

This work contributes to breast cancer sub-type classification using histopathological images. We utilize masked autoencoders (MAEs) to learn a self-supervised embedding tailored for computer vision tasks in this domain. This embedding…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Annalisa Chiocchetti , Marco Dossena , Christopher Irwin , Luigi Portinale

Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover, validate, and control" framework that bridges mechanistic…

Machine Learning · Computer Science 2026-03-10 Vegard Flovik

Implicit SDF-based methods for single-view 3D reconstruction achieve high-quality surfaces but require large labeled datasets, limiting their scalability. We propose MetaSSP, a novel semi-supervised framework that exploits abundant…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Luoxi Zhang , Chun Xie , Itaru Kitahara

Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based autoencoders have shown great potential in detecting anomalies in medical images. However, especially…

Image and Video Processing · Electrical Eng. & Systems 2020-01-03 David Zimmerer , Simon Kohl , Jens Petersen , Fabian Isensee , Klaus Maier-Hein

Motivated by the recent theoretical studies on a two-dimensional (2D) chiral Hamiltonian based on the Su-Schrieffer-Heeger chains, we experimentally and computationally demonstrate that topological flat frequency bands can occur at open…

Mesoscale and Nanoscale Physics · Physics 2020-11-25 Kai Qian , Linghua Zhu , Keun Hyuk Ahn , Camelia Prodan

Masked graph autoencoders have emerged as a powerful graph self-supervised learning method that has yet to be fully explored. In this paper, we unveil that the existing discrete edge masking and binary link reconstruction strategies are…

Machine Learning · Computer Science 2024-02-07 Ziwen Zhao , Yuhua Li , Yixiong Zou , Jiliang Tang , Ruixuan Li

This work describes a novel data-driven latent space inference framework built on paired autoencoders to handle observational inconsistencies when solving inverse problems. Our approach uses two autoencoders, one for the parameter space and…

Machine Learning · Computer Science 2026-01-19 Emma Hart , Bas Peters , Julianne Chung , Matthias Chung

The lack of evidence for new interactions and particles at the Large Hadron Collider has motivated the high-energy physics community to explore model-agnostic data-analysis approaches to search for new physics. Autoencoders are unsupervised…

High Energy Physics - Phenomenology · Physics 2022-05-20 Vishal S. Ngairangbam , Michael Spannowsky , Michihisa Takeuchi

Twisted bilayer systems host a wealth of emergent phenomena, such as flat-band superconductivity, ferromagnetism, and ferroelectricity, arising from moir\'e superlattices and unconventional interlayer coupling. Despite their central role,…

Mesoscale and Nanoscale Physics · Physics 2026-01-21 A. Nakamura , Y. Chiashi , T. Shimojima , Y. Tanaka , S. Akatsuka , M. Sakano , S. Masubuchi , T. Machida , K. Watanabe , T. Taniguchi , K. Ishizaka

Since the discovery of electron-wave duality, electron scattering instrumentation has developed into a powerful array of techniques for revealing the atomic structure of matter. Beyond detecting local lattice variations in equilibrium…