English
Related papers

Related papers: Nilpotent Feed Forward Network Dynamics

200 papers

A new dynamic latent space eigenmodel (LSM) is proposed for weighted temporal networks. The model accommodates integer-valued weights, excess of zeros, time-varying node positions (features), and time-varying network sparsity. The latent…

Methodology · Statistics 2026-04-15 Roberto Casarin , Matteo Iacopini , Antonio Peruzzi

Front form dynamics is not a manifestly rotational invariant formalism. In particular, the requirement of an invariance under rotations around the transverse axes is difficult to fulfill.In the present work it is investigated, to which…

High Energy Physics - Theory · Physics 2009-09-25 Uwe Trittmann , Hans-Christian Pauli

Modern machine learning models are able to outperform humans on a variety of non-trivial tasks. However, as the complexity of the models increases, they consume significant amounts of power and still struggle to generalize effectively to…

Machine Learning · Computer Science 2023-12-13 Thomas Dooms , Ing Jyh Tsang , Jose Oramas

We analyze renormalizability properties of noncommutative (NC) theories with a bifermionic NC parameter. We introduce a new 4-dimensional scalar field model which is renormalizable at all orders of the loop expansion. We show that this…

High Energy Physics - Theory · Physics 2008-11-26 R. Fresneda , D. M. Gitman , D. V. Vassilevich

Incorporating the Forward Forward algorithm into neural network training represents a transformative shift from traditional methods, introducing a dual forward mechanism that streamlines the learning process by bypassing the complexities of…

Machine Learning · Computer Science 2024-09-25 Mitra Bakhshi

We use the method of equivariant moving frames to revisit the problem of normal forms and equivalence of nondegenerate real hypersurfaces M \subset C^2 under the pseudo-group action of holomorphic transformations. The moving frame…

Differential Geometry · Mathematics 2022-02-28 Peter J. Olver , Masoud Sabzevari , Francis Valiquette

We propose a dynamical neural network model with a hierarchical and modular structure. The network architecture can be derived by minimizing an energy function that is originally designed based on two kinds of neurons with quite different…

Neurons and Cognition · Quantitative Biology 2026-04-14 Kazuyoshi Tsutsumi , Ernst Niebur

Complex network theory has been used to study complex systems. However, many real-life systems involve multiple kinds of objects . They can't be described by simple graphs. In order to provide complete information of these systems, we…

Physics and Society · Physics 2015-11-10 Jin-Li Guo , Xin-Yun Zhu

This paper presents a physics-informed neural network approach for dynamic modeling of saturable synchronous machines, including cases with spatial harmonics. We introduce an architecture that incorporates gradient networks directly into…

Systems and Control · Electrical Eng. & Systems 2026-02-17 Junyi Li , Tim Foissner , Floran Martin , Antti Piippo , Marko Hinkkanen

In this work we present an application of modern deep learning methodologies to the numerical solution of partial differential equations in transport models. More specifically, we employ a supervised deep neural network that takes into…

Numerical Analysis · Mathematics 2021-02-10 Eduardo Abreu , Joao B. Florindo

The paper proposes representation functionals in a dual paradigm where learning jointly concerns both linear convolutional weights and parametric forms of nonlinear activation functions. The nonlinear forms proposed for performing the…

Information Retrieval · Computer Science 2021-02-08 Abdourrahmane Mahamane Atto , Sylvie Galichet , Dominique Pastor , Nicolas Méger

It is well known that Lagrangian dynamical systems naturally arise in describing wave front dynamics in the limit of short waves (which is called pseudoclassical limit or limit of geometrical optics). Wave fronts are the surfaces of…

Differential Geometry · Mathematics 2007-05-23 Ruslan Sharipov

Recent works have demonstrated promising performances of neural networks on hyperbolic spaces and symmetric positive definite (SPD) manifolds. These spaces belong to a family of Riemannian manifolds referred to as symmetric spaces of…

Machine Learning · Statistics 2026-01-06 Xuan Son Nguyen , Shuo Yang , Aymeric Histace

We revisit the problem of introducing an a priori control for devices that can be modeled via a symplectic map in a neighborhood of an elliptic equilibrium. Using a technique based on Lie transform methods we produce a normal form algorithm…

Dynamical Systems · Mathematics 2015-12-09 M. Sansottera , A. Giorgilli , T. Carletti

We use string-net models to accomplish a direct, purely two-dimensional, approach to correlators of two-dimensional rational conformal field theories. We obtain concise geometric expressions for the objects describing bulk and boundary…

Quantum Algebra · Mathematics 2022-11-09 Jürgen Fuchs , Christoph Schweigert , Yang Yang

Accurately learning the temporal behavior of dynamical systems requires models with well-chosen learning biases. Recent innovations embed the Hamiltonian and Lagrangian formalisms into neural networks and demonstrate a significant…

Machine Learning · Computer Science 2021-10-04 Shaan Desai , Marios Mattheakis , David Sondak , Pavlos Protopapas , Stephen Roberts

We investigate deformations of four-dimensional N=(1,1) euclidean superspace induced by nonanticommuting fermionic coordinates. We essentially use the harmonic superspace approach and consider nilpotent bi-differential Poisson operators…

High Energy Physics - Theory · Physics 2009-11-10 Evgeny Ivanov , Olaf Lechtenfeld , Boris Zupnik

Patterns forming spontaneously in extended, three-dimensional, dissipative systems are likely to excite several homogeneous soft modes ($\approx$ hydrodynamic modes) of the underlying physical system, much more than quasi one- and…

Pattern Formation and Solitons · Physics 2009-10-31 Axel G. Rossberg

We investigate bifurcations in feedforward coupled cell networks. Feedforward structure (the absence of feedback) can be defined by a partial order on the cells. We use this property to study generic one-parameter steady state bifurcations…

Dynamical Systems · Mathematics 2022-03-14 Sören von der Gracht , Eddie Nijholt , Bob Rink

We investigate the hexagon formalism in the planar 4d conformal fishnet theory. This theory arises from N=4 SYM by a deformation that preserves both conformal symmetry and integrability. Based on this relation, we obtain the hexagon form…

High Energy Physics - Theory · Physics 2020-01-29 Benjamin Basso , Joao Caetano , Thiago Fleury