English
Related papers

Related papers: Networks with complex weights: Green function and …

200 papers

Whilst deep neural networks have shown great empirical success, there is still much work to be done to understand their theoretical properties. In this paper, we study the relationship between random, wide, fully connected, feedforward…

Machine Learning · Statistics 2018-08-17 Alexander G. de G. Matthews , Mark Rowland , Jiri Hron , Richard E. Turner , Zoubin Ghahramani

We consider piecewise linear interpolation from the perspective of kernel interpolation and quadrature. If the Sobolev space $W_2^1(0, 1)$ is equipped with a suitable inner product, its reproducing kernel is piecewise linear and gives rise…

Numerical Analysis · Mathematics 2026-03-03 Toni Karvonen , Gabriele Santin , Tizian Wenzel

The Green's function method is recognized to be a very powerful tool for modelling quantum transport in nanoscale electronic devices. As atomistic calculations are generally expensive, numerical methods and related algorithms have been…

Mesoscale and Nanoscale Physics · Physics 2024-05-24 Viet-Hung Nguyen , Jean-Christophe Charlier

Modeling networks can serve as a means of summarizing high-dimensional complex systems. Adapting an approach devised for dense, weighted networks, we propose a new method for generating and estimating unweighted networks. This approach can…

Physics and Society · Physics 2024-04-12 Benjamin Leinwand , Vince Lyzinski

Deep convolutional networks provide state of the art classifications and regressions results over many high-dimensional problems. We review their architecture, which scatters data with a cascade of linear filter weights and non-linearities.…

Machine Learning · Statistics 2016-04-27 Stéphane Mallat

We study several quantities associated to the Green's function of a multiply connected domain in the complex plane. Among them are some intrinsic properties such as geodesics, curvature, and $L^2$-cohomology of the capacity metric and…

Complex Variables · Mathematics 2016-05-17 Diganta Borah , Pranav Haridas , Kaushal Verma

Heavy-tailed networks, which have degree distributions characterised by slower than exponentially bounded tails, are common in many different situations. Some interesting cases, where heavy tails are characterised by inverse powers…

Physics and Society · Physics 2021-01-21 Ismo T. Koponen , Elina Palmgren , Esko Keski-Vakkuri

In this paper, we study the existence of positive solutions for nonlinear fractional differential equations with a singular weight. We derive Green's function and corresponding integral operator and then examine the compactness of the…

Classical Analysis and ODEs · Mathematics 2022-03-22 Jinsil Lee , Yong-Hoon Lee

Complex-valued neural networks are not a new concept, however, the use of real-valued models has often been favoured over complex-valued models due to difficulties in training and performance. When comparing real-valued versus…

Machine Learning · Computer Science 2018-11-30 Nils Mönning , Suresh Manandhar

We develop Green's function estimate for manifolds satisfying a weighted Poincare inequality together with a compatible lower bound on the Ricci curvature. The estimate is then applied to establish existence and sharp estimates of the…

Differential Geometry · Mathematics 2019-05-01 Ovidiu Munteanu , Chiung-Jue Anna Sung , Jiaping Wang

We study the situations when the solution to a weighted stochastic recursion has a power law tail. To this end, we develop two complementary approaches, the first one extends Goldie's (1991) implicit renewal theorem to cover recursions on…

Probability · Mathematics 2010-07-30 Predrag R. Jelenkovic , Mariana Olvera-Cravioto

Deep neural networks, particularly those employing Rectified Linear Units (ReLU), are often perceived as complex, high-dimensional, non-linear systems. This complexity poses a significant challenge to understanding their internal learning…

Machine Learning · Computer Science 2025-11-11 Longqing Ye

A complex-valued convolutional network (convnet) implements the repeated application of the following composition of three operations, recursively applying the composition to an input vector of nonnegative real numbers: (1) convolution with…

Machine Learning · Computer Science 2016-05-04 Joan Bruna , Soumith Chintala , Yann LeCun , Serkan Piantino , Arthur Szlam , Mark Tygert

We derive two formulas for the weighted sums of rooted spanning forests of particular sequence of graphs by using the matrix tree theorem. We consider cycle graphs with edges so called the pendant edges. One of our formula can be described…

Combinatorics · Mathematics 2024-02-13 Hajime Fujita , Kimiko Hasegawa , Yukie Inaba , Takefumi Kondo

The importance of studying properties of networks is manifest in diverse fields ranging from biology, engineering, physics, chemistry, neuroscience, and medicine. The functionality of networks with regard to performance, throughput,…

Molecular Networks · Quantitative Biology 2015-03-27 Allen Tannenbaum , Chris Sander , Liangjia Zhu , Romeil Sandhu , Ivan Kolesov , Eduard Reznik , Yasin Senbabaoglu , Tryphon Georgiou

The quantum correlations of $N$ noninteracting spinless fermions in their ground state can be expressed in terms of a two-point function called the kernel. Here we develop a general and compact method for computing the kernel in a general…

Statistical Mechanics · Physics 2021-03-05 David S. Dean , Pierre Le Doussal , Satya N. Majumdar , Gregory Schehr , Naftali R. Smith

For decades, complex networks, such as social networks, biological networks, chemical networks, technological networks, have been used to study the evolution and dynamics of different kinds of complex systems. These complex systems can be…

Social and Information Networks · Computer Science 2020-12-16 Akrati Saxena

Complex networks are an important paradigm of modern complex systems sciences which allows quantitatively assessing the structural properties of systems composed of different interacting entities. During the last years, intensive efforts…

We show that an interesting class of feed-forward neural networks can be understood as quantitative argumentation frameworks. This connection creates a bridge between research in Formal Argumentation and Machine Learning. We generalize the…

Neural and Evolutionary Computing · Computer Science 2020-12-11 Nico Potyka

We introduce a general approach to traces that we consider as linear continuous functionals on some function space where we focus on some special choices for that space. This leads to an integral calculus for the computation of the precise…

Analysis of PDEs · Mathematics 2025-10-28 Moritz Schönherr , Friedemann Schuricht