English
Related papers

Related papers: Classifying topological sector via machine learnin…

200 papers

We perform topological data analysis on the internal states of convolutional deep neural networks to develop an understanding of the computations that they perform. We apply this understanding to modify the computations so as to (a) speed…

Machine Learning · Computer Science 2018-11-06 Gunnar Carlsson , Rickard Brüel Gabrielsson

In this paper we approach two relevant deep learning topics: i) tackling of graph structured input data and ii) a better understanding and analysis of deep networks and related learning algorithms. With this in mind we focus on the…

Disordered Systems and Neural Networks · Physics 2018-02-13 Zohar Ringel , Rodrigo de Bem

Deploying neural networks on the edge has become increasingly important as deep learning is being applied in an increasing amount of applications. At the edge computing hardware typically has limited resources disallowing to run neural…

Machine Learning · Computer Science 2025-09-15 Quinten Van Baelen , Peter Karsmakers

The topological susceptibility is an important quantity in QCD, which can be computed using lattice methods. However, at a fine lattice spacing, or when using high quality chirally symmetric quarks, algorithms which proceed in small update…

High Energy Physics - Lattice · Physics 2016-05-30 Arthur Dromard , Wolfgang Bietenholz , Krzysztof Cichy , Marc Wagner

Machine learning potentials have become an important tool for atomistic simulations in many fields, from chemistry via molecular biology to materials science. Most of the established methods, however, rely on local properties and are thus…

Materials Science · Physics 2021-03-17 Tsz Wai Ko , Jonas A. Finkler , Stefan Goedecker , Jörg Behler

It is challenging to directly estimate the human geometry from a single image due to the high diversity and complexity of body shapes with the various clothing styles. Most of model-based approaches are limited to predict the shape and pose…

Computer Vision and Pattern Recognition · Computer Science 2022-02-02 Lixiang Lin , Jianke Zhu

Recently, with convolutional neural networks gaining significant achievements in many challenging machine learning fields, hand-crafted neural networks no longer satisfy our requirements as designing a network will cost a lot, and…

Machine Learning · Computer Science 2018-11-01 Guoqiang Zhong , Wencong Jiao , Wei Gao

We continue our study of the large N phase transition in q-deformed Yang-Mills theory on the sphere and its role in connecting topological strings to black hole entropy. We study in detail the chiral theory defined in terms of uncoupled…

High Energy Physics - Theory · Physics 2010-02-03 Nicola Caporaso , Michele Cirafici , Luca Griguolo , Sara Pasquetti , Domenico Seminara , Richard J. Szabo

The goal of this paper is to analyze the geometric properties of deep neural network classifiers in the input space. We specifically study the topology of classification regions created by deep networks, as well as their associated decision…

Computer Vision and Pattern Recognition · Computer Science 2017-05-29 Alhussein Fawzi , Seyed-Mohsen Moosavi-Dezfooli , Pascal Frossard , Stefano Soatto

Quantum material phases such as the Anderson insulator, diffusive metal, and Weyl/Dirac semimetal as well as topological insulators show specific wave functions both in real and Fourier spaces. These features are well captured by…

Mesoscale and Nanoscale Physics · Physics 2019-11-19 Tomohiro Mano , Tomi Ohtsuki

This work introduces the Topological CNN (TCNN), which encompasses several topologically defined convolutional methods. Manifolds with important relationships to the natural image space are used to parameterize image filters which are used…

Machine Learning · Computer Science 2021-03-05 Ephy R. Love , Benjamin Filippenko , Vasileios Maroulas , Gunnar Carlsson

Quantum machine learning offers a promising advantage in extracting information about quantum states, e.g. phase diagram. However, access to training labels is a major bottleneck for any supervised approach, preventing getting insights…

Quantum Physics · Physics 2023-02-13 Saverio Monaco , Oriel Kiss , Antonio Mandarino , Sofia Vallecorsa , Michele Grossi

Machine learning has made important headway in helping to improve the treatment of quantum many-body systems. A domain of particular relevance are correlated inhomogeneous systems. What has been missing so far is a general, scalable…

Quantum Physics · Physics 2026-02-10 Alex Blania , Sandro Herbig , Fabian Dechent , Evert van Nieuwenburg , Florian Marquardt

After decades of progress and effort, obtaining a phase diagram for a strongly-correlated topological system still remains a challenge. Although in principle one could turn to Wilson loops and long-range entanglement, evaluating these…

Strongly Correlated Electrons · Physics 2017-12-14 Yi Zhang , Roger G. Melko , Eun-Ah Kim

Deep learning models frequently make incorrect predictions with high confidence when presented with test examples that are not well represented in their training dataset. We propose a novel and straightforward approach to estimate…

Machine Learning · Computer Science 2019-10-04 Tiago Ramalho , Miguel Miranda

This paper considers the problem of learning the parameters in Bayesian networks of discrete variables with known structure and hidden variables. Previous approaches in these settings typically use expectation maximization; when the network…

Machine Learning · Computer Science 2013-09-27 Yonatan Halpern , David Sontag

Neural network field theory formulates field theory as a statistical ensemble of fields defined by a network architecture and a density on its parameters. We extend the construction to topological settings via the inclusion of discrete…

High Energy Physics - Theory · Physics 2026-04-06 Christian Ferko , James Halverson , Vishnu Jejjala , Brandon Robinson

A matrix model is constructed to compute characteristic numbers of the space of subsets of $R^d $ with $N$ elements. This matrix model is found to be a constrained null dimensional reduction to a point of a Yang-Mills theory with…

High Energy Physics - Theory · Physics 2007-05-23 Vipul Periwal

We present a numerical method to compute path integrals in effective SU(2) Yang-Mills theories. The basic idea is to approximate the Yang-Mills path integral by summing over all gauge field configurations, which can be represented as a…

High Energy Physics - Phenomenology · Physics 2008-11-26 Marc Wagner

We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a standard gradient-based training. The resulting network has the structure of a graph tailored to the particular learning…

Machine Learning · Computer Science 2020-07-16 Romuald A. Janik , Aleksandra Nowak