English
Related papers

Related papers: Activation Saturation and Floquet Spectrum Collaps…

200 papers

Deep neural networks owe their expressive power to nonlinear activation functions. The effective field theory of signal propagation at initialization reveals a few distinct universality classes of activations that exhibit different depth…

Disordered Systems and Neural Networks · Physics 2026-05-08 Omri Lesser , Debanjan Chowdhury

We investigate disorder effects on Landau levels in Dirac electron systems with the use of a non-Hermitian quasiparticle Hamiltonian formalism. This formalism reveals that spin-dependent scattering rates induce the spectrum collapse of…

Mesoscale and Nanoscale Physics · Physics 2021-06-07 Taiki Matsushita , Yuki Nagai , Satoshi Fujimoto

We study a network of spiking neurons with heterogeneous excitabilities connected via inhibitory delayed pulses. For globally coupled systems the increase of the inhibitory coupling reduces the number of firing neurons by following a Winner…

Disordered Systems and Neural Networks · Physics 2019-05-29 Stefano Luccioli , David Angulo Garcia , Alessandro Torcini

A neural network has an activation bottleneck if one of its hidden layers has a bounded image. We show that networks with an activation bottleneck cannot forecast unbounded sequences such as straight lines, random walks, or any sequence…

Machine Learning · Computer Science 2024-06-05 Maximilian Toller , Hussain Hussain , Bernhard C Geiger

We study the approximation properties of neural ordinary differential equations (neural ODEs) in the space of continuous functions. Since a neural ODE requires input and output dimensions to be the same, while input and output dimensions of…

Numerical Analysis · Mathematics 2026-04-08 Arturo De Marinis , Davide Murari , Elena Celledoni , Nicola Guglielmi , Brynjulf Owren , Francesco Tudisco

Deep feedforward networks initialized along the edge of chaos exhibit exponentially superior training ability as quantified by maximum trainable depth. In this work, we explore the effect of saturation of the tanh activation function along…

Machine Learning · Computer Science 2023-04-13 Aleksandar Bukva , Jurriaan de Gier , Kevin T. Grosvenor , Ro Jefferson , Koenraad Schalm , Eliot Schwander

We observe and study a self-organized phenomenon whereby the activity in a network of spiking neurons spontaneously terminates. We consider different types of populations, consisting of bistable model neurons connected electrically by gap…

Disordered Systems and Neural Networks · Physics 2018-11-22 Muhammet Uzuntarla , Joaquin J. Torres , Ali Çalım , Ernest Barreto

The hippocampus has the capacity for reactivating recently acquired memories [1-3] and it is hypothesized that one of the functions of sleep reactivation is the facilitation of consolidation of novel memory traces [4-11]. The dynamic and…

Neurons and Cognition · Quantitative Biology 2015-06-26 Piotr Jablonski , Gina R. Poe , Michal Zochowski

Despite broad interest in applying deep learning techniques to scientific discovery, learning interpretable formulas that accurately describe scientific data is very challenging because of the vast landscape of possible functions and the…

Machine Learning · Computer Science 2021-02-17 Fuchang Gao , Boyu Zhang

We derive bounds on the error, in high-order Sobolev norms, incurred in the approximation of Sobolev-regular as well as analytic functions by neural networks with the hyperbolic tangent activation function. These bounds provide explicit…

Numerical Analysis · Mathematics 2021-12-09 Tim De Ryck , Samuel Lanthaler , Siddhartha Mishra

We consider feed-forward neural networks with one hidden layer, tree architecture and a fixed hidden-to-output Boolean function. Focusing on the saturation limit of the storage problem the influence of replica symmetry breaking on the…

Disordered Systems and Neural Networks · Physics 2009-10-31 D. Malzahn , A. Engel

Fully-connected deep neural networks with weights initialized from independent Gaussian distributions can be tuned to criticality, which prevents the exponential growth or decay of signals propagating through the network. However, such…

Machine Learning · Computer Science 2024-06-13 Hannah Day , Yonatan Kahn , Daniel A. Roberts

We investigate why deep neural networks suffer from loss of plasticity in deep continual learning, failing to learn new tasks without reinitializing parameters. We show that this failure is preceded by Hessian spectral collapse at new-task…

Machine Learning · Computer Science 2025-09-30 Naicheng He , Kaicheng Guo , Arjun Prakash , Saket Tiwari , Ruo Yu Tao , Tyrone Serapio , Amy Greenwald , George Konidaris

In this paper we prove that, in the deep limit, the stochastic gradient descent on a ResNet type deep neural network, where each layer shares the same weight matrix, converges to the stochastic gradient descent for a Neural ODE and that the…

Machine Learning · Statistics 2020-01-22 Benny Avelin , Kaj Nyström

We investigate the regularity of spontaneous spiking activity on Newman-Watts small-world networks consisting of biophysically realistic Hodgkin-Huxley neurons with a tunable intensity of intrinsic noise and fraction of blocked…

Biological Physics · Physics 2009-06-05 Mahmut Ozer , Matjaz Perc , Muhammet Uzuntarla

We continue the work of a series of previous studies of a mathematical model that describes the mean-field limit behavior of a homogeneous network of excitatory point spiking neurons. Contrary to other models, here noise is intrinsic to the…

Neurons and Cognition · Quantitative Biology 2017-07-20 Guillem Via

Recent analyses of neural networks with shaped activations (i.e. the activation function is scaled as the network size grows) have led to scaling limits described by differential equations. However, these results do not a priori tell us…

Machine Learning · Statistics 2024-04-22 Mufan Bill Li , Mihai Nica

We demonstrate a phenomenon of condensation of the Fourier transform $\widehat{f}$ of a function $f$ defined on the real line $\mathbb{R}$ which decreases rapidly on one half of the line. For instance, we prove that if $f$ is…

Complex Variables · Mathematics 2023-11-28 Bartosz Malman

The logit outputs of a feedforward neural network at initialization are conditionally Gaussian, given a random covariance matrix defined by the penultimate layer. In this work, we study the distribution of this random matrix. Recent work…

Machine Learning · Statistics 2023-06-16 Mufan Bill Li , Mihai Nica , Daniel M. Roy

The paper discusses the use of the Absolute activation function in classification neural networks. An examples are shown of using this activation function in simple and more complex problems. Using as a baseline LeNet-5 network for solving…

Machine Learning · Computer Science 2023-04-25 Oleg I. Berngardt