English
Related papers

Related papers: Complexity of deep computations via topology of fu…

200 papers

While concepts and tools from Theoretical Computer Science are regularly applied to, and significantly support, software development for discrete problems, Numerical Engineering largely employs recipes and methods whose correctness and…

Computational Complexity · Computer Science 2018-01-23 Akitoshi Kawamura , Martin Ziegler

We define a class of spaces on which one may generalise the notion of compactness following motivating examples from higher-dimensional number theory. We establish analogues of several well-known topological results (such as Tychonoff's…

General Topology · Mathematics 2019-02-11 Raven Waller

The utilization of statistical methods an their applications within the new field of study known as Topological Data Analysis has has tremendous potential for broadening our exploration and understanding of complex, high-dimensional data…

Applications · Statistics 2016-07-19 Patrick S. Medina , R. W. Doerge

Despite encouraging recent progresses in ensemble approaches, classification methods seem to have reached a plateau in development. Further advances depend on a better understanding of geometrical and topological characteristics of point…

Computer Vision and Pattern Recognition · Computer Science 2007-05-23 Tin Kam Ho

Computational feasibility is a widespread concern that guides the framing and modeling of biological and artificial intelligence. The specification of cognitive system capacities is often shaped by unexamined intuitive assumptions about the…

Artificial Intelligence · Computer Science 2022-05-12 Federico Adolfi , Todd Wareham , Iris van Rooij

The notion of effective topological complexity, introduced by B{\l}aszczyk and Kaluba, deals with using group actions in the configuration space in order to reduce the complexity of the motion planning algorithm. In this article we focus on…

Algebraic Topology · Mathematics 2024-03-14 Zbigniew Błaszczyk , Arturo Espinosa Baro , Antonio Viruel

We construct a category that classifies compact Hausdorff spaces by their shape and finite topological spaces by their weak homotopy type.

Category Theory · Mathematics 2021-10-07 Pedro J. Chocano , Manuel A. Morón , Francisco R. Ruiz del Portal

Compositionality is a key property for dealing with complexity, which has been studied from many points of view in diverse fields. Particularly, the composition of individual computations (or programs) has been widely studied almost since…

Logic in Computer Science · Computer Science 2022-06-06 Damian Arellanes

We consider functions defined by deep neural networks as definable objects in an o-miminal expansion of the real field, and derive an almost linear (in the number of weights) bound on sample complexity of such networks.

Machine Learning · Computer Science 2019-10-25 Alexander Usvyatsov

Various limit-free formulas are given for the computation of the algebraic and the topological entropy, respectively in the settings of endomorphisms of locally finite discrete groups and of continuous endomorphisms of totally disconnected…

Dynamical Systems · Mathematics 2012-05-23 Dikran Dikranjan , Anna Giordano Bruno

The paper aims to investigate relevant computational issues of deep neural network architectures with an eye to the interaction between the optimization algorithm and the classification performance. In particular, we aim to analyze the…

Optimization and Control · Mathematics 2024-05-06 Corrado Coppola , Lorenzo Papa , Marco Boresta , Irene Amerini , Laura Palagi

Topological deep learning is a formalism that is aimed at introducing topological language to deep learning for the purpose of utilizing the minimal mathematical structures to formalize problems that arise in a generic deep learning…

Machine Learning · Computer Science 2021-02-17 Mustafa Hajij , Kyle Istvan

Topology may be interpreted as the study of verifiability, where opens correspond to semi-decidable properties. In this paper we make a distinction between verifiable properties themselves and processes which carry out the verification…

General Topology · Mathematics 2026-04-15 Peter F. Faul , Graham Manuell

Higher category theory is an exceedingly active area of research, whose rapid growth has been driven by its penetration into a diverse range of scientific fields. Its influence extends through key mathematical disciplines, notably homotopy…

Category Theory · Mathematics 2017-07-07 Simona Paoli

We establish some upper and lower bounds of the rational topological complexity for certain classes of elliptic spaces. Our techniques permit us in particular to show that the rational topological complexity coincides with the dimension of…

Algebraic Topology · Mathematics 2022-07-05 Said Hamoun , Youssef Rami , Lucile Vandembroucq

In many areas of applied geometric/numeric computational mathematics, including geo-mapping, computer vision, computer graphics, finite element analysis, medical imaging, geometric design, and solid modeling, one has to compute incidences,…

Computational Geometry · Computer Science 2019-11-20 Alberto Paoluzzi , Vadim Shapiro , Antonio DiCarlo , Francesco Furiani , Giulio Martella , Giorgio Scorzelli

Various kinds of data are routinely represented as discrete probability distributions. Examples include text documents summarized by histograms of word occurrences and images represented as histograms of oriented gradients. Viewing a…

Computational Geometry · Computer Science 2019-03-29 Herbert Edelsbrunner , Ziga Virk , Hubert Wagner

The theory of computational complexity focuses on functions and, hence, studies programs whose interactive behavior is reduced to a simple question/answer pattern. We propose a broader theory whose ultimate goal is expressing and analyzing…

Computational Complexity · Computer Science 2012-09-05 Ugo Dal Lago , Tobias Heindel , Damiano Mazza , Daniele Varacca

We specialize techniques from topological data analysis to the problem of characterizing the topological complexity (as defined in the body of the paper) of a multi-class data set. As a by-product, a topological classifier is defined that…

Machine Learning · Computer Science 2024-06-10 Christopher Griffin , Trevor Karn , Benjamin Apple

The spatial character of territorial systems plays a crucial role in the emergence of their complexities. This contribution aims at illustrating to what extent different types of complexities can be exhibited in models of such systems. We…

Physics and Society · Physics 2019-01-29 Juste Raimbault