English
Related papers

Related papers: Activation Saturation and Floquet Spectrum Collaps…

200 papers

Existing works on the expressive power of neural networks typically assume real parameters and exact operations. In this work, we study the expressive power of quantized networks under discrete fixed-point parameters and inexact fixed-point…

Machine Learning · Computer Science 2026-01-21 Yeachan Park , Sejun Park , Geonho Hwang

We propose a novel methodology to solve a key eigenvalue optimization problem which arises in the contractivity analysis of neural ODEs. When looking at contractivity properties of a one layer weight-tied neural ODE…

Numerical Analysis · Mathematics 2024-12-20 Nicola Guglielmi , Arturo De Marinis , Anton Savostianov , Francesco Tudisco

We investigate the effects of the saturation boundary on small-x evolution at the next-to-leading order accuracy and beyond. We demonstrate that the instabilities of the next-to-leading order BFKL evolution are not cured by the presence of…

High Energy Physics - Phenomenology · Physics 2015-05-28 E. Avsar , A. M. Stasto , D. N. Triantafyllopoulos , D. Zaslavsky

This paper studies the approximation capacity of neural networks with an arbitrary activation function and with norm constraint on the weights. Upper and lower bounds on the approximation error of these networks are computed for smooth…

Numerical Analysis · Mathematics 2025-12-24 Francesco Paolo Maiale , Anastasiia Trofimova , Arturo De Marinis

Pre-trained Transformers often exhibit over-confidence in source patterns and difficulty in forming new target-domain patterns during fine-tuning. We formalize the mechanism of output saturation leading to gradient suppression through…

Machine Learning · Computer Science 2025-11-04 Wang Zixian

We analyze the linear response of a half filled Landau level to long wavelength and low frequency driving forces, using Fermi liquid theory for composite fermions. This response is determined by the composite fermions quasi--particle…

Condensed Matter · Physics 2009-10-28 Ady Stern , Bertrand I. Halperin

There has been a growing interest in expressivity of deep neural networks. However, most of the existing work about this topic focuses only on the specific activation function such as ReLU or sigmoid. In this paper, we investigate the…

Machine Learning · Statistics 2019-07-24 Ilsang Ohn , Yongdai Kim

We study numerically the effects of time delay in networks of delay-coupled excitable FitzHugh Nagumo systems with dissipation. The generation of periodic self-sustained oscillations and its threshold are analyzed depending on the…

Adaptation and Self-Organizing Systems · Physics 2023-07-19 A. V. Bukh , I. A. Shepelev , E. M. Elizarov , S. S. Muni , E. Schöll , G. I. Strelkova

The continuous integration of experimental data into coherent models of the brain is an increasing challenge of modern neuroscience. Such models provide a bridge between structure and activity, and identify the mechanisms giving rise to…

Neurons and Cognition · Quantitative Biology 2017-03-03 Jannis Schuecker , Maximilian Schmidt , Sacha J. van Albada , Markus Diesmann , Moritz Helias

A new non-linear variant of a quantitative extension of the uniform boundedness principle is used to show sharpness of error bounds for univariate approximation by sums of sigmoid and ReLU functions. Single hidden layer feedforward neural…

Functional Analysis · Mathematics 2020-06-18 Steffen Goebbels

We study the strong disorder regime of Floquet topological systems in dimension two, that describe independent electrons on a lattice subject to a periodic driving. In the spectrum of the Floquet propagator we assume the existence of an…

Mathematical Physics · Physics 2019-06-26 Jacob Shapiro , Clément Tauber

We prove a Quantitative Functional Central Limit Theorem for one-hidden-layer neural networks with generic activation function. The rates of convergence that we establish depend heavily on the smoothness of the activation function, and they…

Probability · Mathematics 2023-07-06 Valentina Cammarota , Domenico Marinucci , Michele Salvi , Stefano Vigogna

The success of deep networks has been attributed in part to their expressivity: per parameter, deep networks can approximate a richer class of functions than shallow networks. In ReLU networks, the number of activation patterns is one…

Machine Learning · Statistics 2019-10-22 Boris Hanin , David Rolnick

Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural…

Machine Learning · Computer Science 2019-05-21 MohamadAli Torkamani , Phillip Wallis , Shiv Shankar , Amirmohammad Rooshenas

Networks of model neurons with balanced recurrent excitation and inhibition produce irregular and asynchronous spiking activity. We extend the analysis of balanced networks to include the known dependence of connection probability on the…

Neurons and Cognition · Quantitative Biology 2014-06-02 Robert Rosenbaum , Brent Doiron

In this paper, we introduce a novel non-linear activation function that spontaneously induces class-compactness and regularization in the embedding space of neural networks. The function is dubbed DOME for Difference Of Mirrored Exponential…

Machine Learning · Computer Science 2021-12-08 Mohamed E. Hussein , Wael AbdAlmageed

We theoretically study the excitation spectrum of confined macroscopic optical lattices in the Mott-insulating limit. For large systems, a fast numerical method is proposed to calculate the ground state filling and excitation energies. We…

Quantum Gases · Physics 2009-06-30 Dirk-Sören Lühmann , Kai Bongs , Daniela Pfannkuche

We revisit Heisenberg's model for nucleon-nucleon scattering which admits a saturation of the Froissart bound. We examine its uniqueness, and find that up to certain natural generalizations, it is the only action that saturates the bound.…

High Energy Physics - Theory · Physics 2015-11-25 Horatiu Nastase , Jacob Sonnenschein

Objective. Long-term potentiation (LTP) is a fundamental mechanism underlying learning and memory, yet its investigation at the network level in vitro remains challenging, particularly when optogenetic stimulation is used. The objective of…

Biological Physics · Physics 2026-02-13 Matteo Dominici , Ilya Auslender , Clara Zaccaria , Yasaman Heydari , Lorenzo Pavesi

Efficient pattern separation in dentate gyrus plays an important role in storing information in the hippocampus. Current knowledge of the structure and function of the hippocampus, entorhinal cortex and dentate gyrus, in pattern separation…

Neurons and Cognition · Quantitative Biology 2018-08-02 Faramarz Faghihi , Homa Samani , Ahmed A. Moustafa