English
Related papers

Related papers: Fading memory and the convolution theorem

200 papers

We characterize ultrafilter convergence and ultrafilter compactness in linearly ordered and generalized ordered topological spaces. In such spaces, and for every ultrafilter $D$, the notions of $D$-compactness and of $D$-pseudocompactness…

General Topology · Mathematics 2016-08-30 Paolo Lipparini

This paper is a cursory study on how topological features are preserved within the internal representations of neural network layers. Using techniques from topological data analysis, namely persistent homology, the topological features of a…

Machine Learning · Computer Science 2022-08-16 Archie Shahidullah

Represented spaces form the general setting for the study of computability derived from Turing machines. As such, they are the basic entities for endeavors such as computable analysis or computable measure theory. The theory of represented…

Logic · Mathematics 2015-03-04 Arno Pauly

Bloom filters are widely used data structures that compactly represent sets of elements. Querying a Bloom filter reveals if an element is not included in the underlying set or is included with a certain error rate. This membership testing…

Databases · Computer Science 2022-08-08 Angjela Davitkova , Damjan Gjurovski , Sebastian Michel

A suitable feature representation that can both preserve the data intrinsic information and reduce data complexity and dimensionality is key to the performance of machine learning models. Deeply rooted in algebraic topology, persistent…

Algebraic Topology · Mathematics 2018-11-02 Chi Seng Pun , Kelin Xia , Si Xian Lee

In lifelong learning, tasks (or classes) to be learned arrive sequentially over time in arbitrary order. During training, knowledge from previous tasks can be captured and transferred to subsequent ones to improve sample efficiency. We…

Machine Learning · Computer Science 2022-03-02 Xinyuan Cao , Weiyang Liu , Santosh S. Vempala

Techniques from computational topology, in particular persistent homology, are becoming increasingly relevant for data analysis. Their stable metrics permit the use of many distance-based data analysis methods, such as multidimensional…

Algebraic Topology · Mathematics 2021-01-20 Bastian Rieck , Filip Sadlo , Heike Leitte

In parallel with the success of CNNs to solve vision problems, there is a growing interest in developing methodologies to understand and visualize the internal representations of these networks. How the responses of a trained CNN encode the…

Computer Vision and Pattern Recognition · Computer Science 2015-11-18 Ivet Rafegas , Maria Vanrell

This thesis addresses the theory of topological spaces and the foundations of persistence theory. We will discuss chain complexes and the associated simplicial homology groups, as well as their relationship with singular homology theory.…

Algebraic Topology · Mathematics 2024-10-14 Luciano Melodia

We introduce two novel concepts, topological difference and topological correlation, that offer a new perspective on the discriminative power of multiparameter persistence. The former quantifies the discrepancy between multiparameter and…

Algebraic Topology · Mathematics 2025-06-23 Isabella Mastroianni , Ulderico Fugacci

The free metaplectic transformation (FMT) is widely used in many fields such as filter design, pattern recognition, image processing and optics. In order to obtain a more concise and intuitive convolution form, this paper studies two kinds…

General Mathematics · Mathematics 2022-06-28 Hui Zhao , Bing-Zhao Li

Continual learning is an emerging topic in the field of deep learning, where a model is expected to learn continuously for new upcoming tasks without forgetting previous experiences. This field has witnessed numerous advancements, but few…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Aupendu Kar , Krishnendu Ghosh , Prabir Kumar Biswas

The expansion of artificial intelligence (AI) has raised concerns about transparency, accountability, and interpretability, with counterfactual reasoning emerging as a key approach to addressing these issues. However, current mathematical,…

Artificial Intelligence · Computer Science 2025-02-25 JaeHong Kim

Transformers pretrained via next token prediction learn to factor their world into parts, representing these factors in orthogonal subspaces of the residual stream. We formalize two representational hypotheses: (1) a representation in the…

In the present paper, as we did previously in [7], we investigate the relations between the geometric properties of tilings and the algebraic properties of associated relational structures. Our study is motivated by the existence of…

Metric Geometry · Mathematics 2010-02-19 Francis Oger

The study presents a vector-valued extension of the classical Mercer theorem within the framework of reproducing kernel Hilbert spaces defined over Kaplansky-Hilbert modules associated with the algebra of essentially bounded measurable…

Functional Analysis · Mathematics 2025-11-24 A. Arziev , K. Kudaybergenov. P. Orinbaev

In this paper, we propose an extension of the standard strong and weak lack-of-memory properties. We say that the survival function $\bar{F}$ of the vector $(X,Y)$ satisfies pseudo lack-of-memory property in strong version if…

Probability · Mathematics 2024-06-17 Massimo Ricci

We develop and investigate a general theory of representations of second-order functionals, based on a notion of a right comodule for a monad on the category of containers. We show how the notion of comodule representability naturally…

Logic in Computer Science · Computer Science 2025-06-12 Danel Ahman , Andrej Bauer

Various features of the development of individual living species, including individual humans, are programmed. Is death also programmed, and if yes, how is it implemented and what can be the underlying mechanism providing the inevitability…

Chaotic Dynamics · Physics 2019-05-23 Mark Edelman

This paper reviews the functional aspects of statistical learning theory. The main point under consideration is the nature of the hypothesis set when no prior information is available but data. Within this framework we first discuss about…

Machine Learning · Statistics 2016-11-25 Stephane Canu , Xavier Mary , Alain Rakotomamonjy