English
Related papers

Related papers: Fixed points of nonnegative neural networks

200 papers

We study the fixed point problem for a system of multivariate operators that are coordinate-wise monotone (i.e., nondecreasing or nonincreasing in each of the variables, independently), in the setting of quasi-ordered sets. We show that…

General Topology · Mathematics 2012-09-03 Mircea-Dan Rus

Training deep neural networks results in strong learned representations that show good generalization capabilities. In most cases, training involves iterative modification of all weights inside the network via back-propagation. In Extreme…

Machine Learning · Computer Science 2018-02-06 Amir Rosenfeld , John K. Tsotsos

Well-founded fixed points have been used in several areas of knowledge representation and reasoning and to give semantics to logic programs involving negation. They are an important ingredient of approximation fixed point theory. We study…

Discrete Mathematics · Computer Science 2015-12-02 Arnaud Carayol , Zoltan Esik

Neural network is a dynamical system described by two different types of degrees of freedom: fast-changing non-trainable variables (e.g. state of neurons) and slow-changing trainable variables (e.g. weights and biases). We show that the…

Machine Learning · Computer Science 2022-04-06 Vitaly Vanchurin

Neural network methods are increasingly applied to solve phase transition problems, particularly in identifying critical points in non-equilibrium phase transitions, offering more convenience compared to traditional methods. In this paper,…

Statistical Mechanics · Physics 2025-03-12 Feng Gao , Jianmin Shen , Shanshan Wang , Wei Li , Dian Xu

Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal…

Machine Learning · Statistics 2019-10-29 Raanan Y. Rohekar , Yaniv Gurwicz , Shami Nisimov , Gal Novik

In this short paper, we prove fixed point theorems for nonexpansive mappings whose domains are unbounded subsets of Banach spaces. These theorems are generalizations of Penot's result in [Proc. Amer. Math. Soc., 131 (2003), 2371--2377].

Functional Analysis · Mathematics 2007-05-23 Tomonari Suzuki

Nonexpansive mappings play a central role in modern optimization and monotone operator theory because their fixed points can describe solutions to optimization or critical point problems. It is known that when the mappings are sufficiently…

Functional Analysis · Mathematics 2020-04-28 Salihah Alwadani , Heinz H. Bauschke , Xianfu Wang

Following the definition of perturbed metric space, in this paper, some fixed point theorems are established for $ F $-perturbed mappings in complete perturbed metric spaces and justify the result by counter example. Finally, an application…

Metric Geometry · Mathematics 2026-04-06 Dipti Barman , T. Bag

This work presents a novel methodology for analysis and control of nonlinear fluid systems using neural networks. The approach is demonstrated on four different study cases being the Lorenz system, a modified version of the…

Fluid Dynamics · Physics 2023-08-28 Tarcísio Déda , William Wolf , Scott Dawson

This work considers the robustness of uncertain consensus networks. The first set of results studies the stability properties of consensus networks with negative edge weights. We show that if either the negative weight edges form a cut in…

Optimization and Control · Mathematics 2015-03-03 Daniel Zelazo , Mathias Bürger

We analyze the topological properties of the set of functions that can be implemented by neural networks of a fixed size. Surprisingly, this set has many undesirable properties. It is highly non-convex, except possibly for a few exotic…

General Topology · Mathematics 2020-01-24 Philipp Petersen , Mones Raslan , Felix Voigtlaender

Neural networks are powerful function estimators, leading to their status as a paradigm of choice for modeling structured data. However, unlike other structured representations that emphasize the modularity of the problem -- e.g., factor…

Machine Learning · Computer Science 2022-06-20 Tsvetomila Mihaylova , Vlad Niculae , André F. T. Martins

In recent times, neural networks have become a powerful tool for the analysis of complex and abstract data models. However, their introduction intrinsically increases our uncertainty about which features of the analysis are model-related…

Machine Learning · Statistics 2020-11-09 Tom Charnock , Laurence Perreault-Levasseur , François Lanusse

Deep neural networks are powerful tools to model observations over time with non-linear patterns. Despite the widespread use of neural networks in such settings, most theoretical developments of deep neural networks are under the assumption…

Machine Learning · Statistics 2022-10-24 Mingliang Ma , Abolfazl Safikhani

The Kuramoto model when considered over the full space of phase angles [$0,2\pi$) can have multiple stable fixed points which form basins of attraction in the solution space. In this paper we illustrate the fundamentally complex…

Mathematical Physics · Physics 2015-02-25 Richard Taylor

Consider the continuum of points along the edges of a network, i.e., an undirected graph with positive edge weights. We measure distance between these points in terms of the shortest path distance along the network, known as the network…

Computational Geometry · Computer Science 2014-11-07 Prosenjit Bose , Kai Dannies , Jean-Lou De Carufel , Christoph Doell , Carsten Grimm , Anil Maheshwari , Stefan Schirra , Michiel Smid

Expressive querying of machine learning models - viewed as a form of intentional data - enables their verification and interpretation using declarative languages, thereby making learned representations of data more accessible. Motivated by…

Logic in Computer Science · Computer Science 2026-01-07 Martin Grohe , Christoph Standke , Juno Steegmans , Jan Van den Bussche

Network backbones provide useful sparse representations of weighted networks by keeping only their most important links, permitting a range of computational speedups and simplifying network visualizations. A key limitation of existing…

Social and Information Networks · Computer Science 2025-06-13 Alec Kirkley

The classical universal approximation (UA) theorem for neural networks establishes mild conditions under which a feedforward neural network can approximate a continuous function $f$ with arbitrary accuracy. A recent result shows that neural…

Machine Learning · Computer Science 2026-01-28 Geonho Hwang , Wonyeol Lee , Yeachan Park , Sejun Park , Feras Saad
‹ Prev 1 4 5 6 7 8 10 Next ›