English
Related papers

Related papers: Learning Topological Invariance

200 papers

Inferring topological and geometrical information from data can offer an alternative perspective on machine learning problems. Methods from topological data analysis, e.g., persistent homology, enable us to obtain such information,…

Computer Vision and Pattern Recognition · Computer Science 2018-02-19 Christoph Hofer , Roland Kwitt , Marc Niethammer , Andreas Uhl

Existing convolution techniques in artificial neural networks suffer from huge computation complexity, while the biological neural network works in a much more powerful yet efficient way. Inspired by the biological plasticity of dendritic…

Computer Vision and Pattern Recognition · Computer Science 2023-01-16 Rongzhen Zhao , Zhenzhi Wu , Qikun Zhang

This article aims to study the topological invariant properties encoded in node graph representational embeddings by utilizing tools available in persistent homology. Specifically, given a node embedding representation algorithm, we…

Machine Learning · Computer Science 2021-10-12 Mustafa Hajij , Ghada Zamzmi , Xuanting Cai

It has been argued based on electric-magnetic duality and other ingredients that the Jones polynomial of a knot in three dimensions can be computed by counting the solutions of certain gauge theory equations in four dimensions. Here, we…

High Energy Physics - Theory · Physics 2015-05-28 Davide Gaiotto , Edward Witten

Simulated configurations of flexible knotted rings confined inside a spherical cavity are fed into long-short term memory neural networks (LSTM NNs) designed to distinguish knot types. The results show that they perform well in knot…

Soft Condensed Matter · Physics 2023-04-12 Anna Braghetto , Sumanta Kundu , Marco Baiesi , Enzo Orlandini

In certain situations, neural networks are trained upon data that obey underlying symmetries. However, the predictions do not respect the symmetries exactly unless embedded in the network structure. In this work, we introduce architectures…

Machine Learning · Computer Science 2022-04-28 Anwesh Bhattacharya , Marios Mattheakis , Pavlos Protopapas

In this paper, we approach the challenging problem of motion planning for knot tying. We propose a hierarchical approach in which the top layer produces a topological plan and the bottom layer translates this plan into continuous robot…

Robotics · Computer Science 2020-10-07 Mengyuan Yan , Gen Li , Yilin Zhu , Jeannette Bohg

We present an application of invariant polynomials in machine learning. Using the methods developed in previous work, we obtain two types of generators of the Lorentz- and permutation-invariant polynomials in particle momenta; minimal…

High Energy Physics - Phenomenology · Physics 2021-04-27 Ward Haddadin

The topological framework of circuit topology has recently been introduced to complement knot theory and to help in understanding the physics of molecular folding. Naturally evolved linear molecular chains, such as proteins and nucleic…

Geometric Topology · Mathematics 2021-09-07 Alireza Mashaghi , Roland van der Veen

In traditional Graph Neural Networks (GNN), graph convolutional learning is carried out through topology-driven recursive node content aggregation for network representation learning. In reality, network topology and node content are not…

Social and Information Networks · Computer Science 2020-03-31 Min Shi , Yufei Tang , Xingquan Zhu

Classical knot theory deals with {\em diagrams} and {\em invariants}. By means of horizontal {\em trisecants}, we construct a new theory of classical braids with invariants valued in {\em pictures}. These pictures are closely related to…

Geometric Topology · Mathematics 2015-01-22 Vassily Olegovich Manturov

Many learning algorithms have invariances: when their training data is transformed in certain ways, the function they learn transforms in a predictable manner. Here we formalize this notion using concepts from the mathematical field of…

Machine Learning · Computer Science 2019-05-07 Kenneth D. Harris

Establishing correspondences between two images requires both local and global spatial context. Given putative correspondences of feature points in two views, in this paper, we propose Order-Aware Network, which infers the probabilities of…

Computer Vision and Pattern Recognition · Computer Science 2019-08-15 Jiahui Zhang , Dawei Sun , Zixin Luo , Anbang Yao , Lei Zhou , Tianwei Shen , Yurong Chen , Long Quan , Hongen Liao

Despite significant advances in the field of deep learning in applications to various fields, explaining the inner processes of deep learning models remains an important and open question. The purpose of this article is to describe and…

Machine Learning · Computer Science 2022-04-20 German Magai , Anton Ayzenberg

We present a new technique that enables manifold learning to accurately embed data manifolds that contain holes, without discarding any topological information. Manifold learning aims to embed high dimensional data into a lower dimensional…

Robotics · Computer Science 2022-03-11 Thomas Cohn , Nikhil Devraj , Odest Chadwicke Jenkins

This work is dedicated to the consideration of the construction of a representation of braid group generators from vertex models with $N$-states, which provides a great way to study the knot invariant. An algebraic formula is proposed for…

Statistical Mechanics · Physics 2022-04-20 T. K. Kassenova , P. Tsyba , O. Razina , R. Myrzakulov

The network embedding task is to represent the node in the network as a low-dimensional vector while incorporating the topological and structural information. Most existing approaches solve this problem by factorizing a proximity matrix,…

Machine Learning · Computer Science 2022-09-01 Yuchen Liang , Dmitry Krotov , Mohammed J. Zaki

We extend knot contact homology to a theory over the ring $\mathbb{Z}[\lambda^{\pm 1},\mu^{\pm 1}]$, with the invariant given topologically and combinatorially. The improved invariant, which is defined for framed knots in $S^3$ and can be…

Geometric Topology · Mathematics 2008-06-11 Lenhard Ng

Supervised machine learning (ML) methods are emerging as valid alternatives to standard mathematical methods for identifying knots in long, collapsed polymers. Here, we introduce a hybrid supervised/unsupervised ML approach for knot…

Statistical Mechanics · Physics 2025-12-04 Anna Braghetto , Sumanta Kundu , Marco Baiesi , Enzo Orlandini

Recently, graph neural networks (GNNs) have proved to be suitable in tasks on unstructured data. Particularly in tasks as community detection, node classification, and link prediction. However, most GNN models still operate with static…

Machine Learning · Computer Science 2019-06-07 Darwin Saire Pilco , Adín Ramírez Rivera
‹ Prev 1 3 4 5 6 7 10 Next ›