English
Related papers

Related papers: Activation Saturation and Floquet Spectrum Collaps…

200 papers

The strong boundary normalized condition of wavefunction for fully occupied semicore 3d orbitals leads the linear response DFT+U on such metal oxide to have an insurmountable obstacle in Hubbard U determination. We treated the orbital…

Strongly Correlated Electrons · Physics 2015-11-17 Bolong Huang

The generalized Floquet approach is developed to study memory effect on electron transport phenomena through a periodically driven single quantum dot in an electrode-multi-level dot-electrode nanoscale quantum device. The memory effect is…

Mesoscale and Nanoscale Physics · Physics 2015-05-20 Hsing-Ta Chen , Tak-San Ho , Shih-I Chu

We derive approximation bounds for learning single neuron models using thresholded gradient descent when both the labels and the covariates are possibly corrupted adversarially. We assume the data follows the model $y =…

Machine Learning · Statistics 2024-09-06 Arvind Rathnashyam , Alex Gittens

The choice of architecture of a neural network influences which functions will be realizable by that neural network and, as a result, studying the expressiveness of a chosen architecture has received much attention. In ReLU neural networks,…

Machine Learning · Computer Science 2024-12-18 Natalie Brownlowe , Christopher R. Cornwell , Ethan Montes , Gabriel Quijano , Grace Stulman , Na Zhang

This paper investigates the approximation properties of shallow neural networks with activation functions that are powers of exponential functions. It focuses on the dependence of the approximation rate on the dimension and the smoothness…

Machine Learning · Computer Science 2025-10-22 Jian Lu , Xiaohuang Huang

The analysis of the channel capacity in the absence of prior channel knowledge (noncoherent channel) has gained increasing interest in recent years, but it is still unknown for the general case. In this paper we derive bounds on the…

Information Theory · Computer Science 2011-07-05 Itsik Bergel , Sergio Benedetto

The weight initialization and the activation function of deep neural networks have a crucial impact on the performance of the training procedure. An inappropriate selection can lead to the loss of information of the input during forward…

Machine Learning · Statistics 2019-05-28 Soufiane Hayou , Arnaud Doucet , Judith Rousseau

Lipschitz-constrained neural networks have several advantages over unconstrained ones and can be applied to a variety of problems, making them a topic of attention in the deep learning community. Unfortunately, it has been shown both…

Machine Learning · Computer Science 2023-12-20 Stanislas Ducotterd , Alexis Goujon , Pakshal Bohra , Dimitris Perdios , Sebastian Neumayer , Michael Unser

The scope of research in the domain of activation functions remains limited and centered around improving the ease of optimization or generalization quality of neural networks (NNs). However, to develop a deeper understanding of deep…

Machine Learning · Computer Science 2020-12-10 Mohit Goyal , Rajan Goyal , Brejesh Lall

We compute the Floquet Hamiltonian $H_F$ for weakly interacting fermions subjected to a continuous periodic drive using a Floquet perturbation theory (FPT) with the interaction amplitude being the perturbation parameter. This allows us to…

Strongly Correlated Electrons · Physics 2021-01-04 Roopayan Ghosh , Bhaskar Mukherjee , K. Sengupta

We rigorously prove a central limit theorem for neural network models with a single hidden layer. The central limit theorem is proven in the asymptotic regime of simultaneously (A) large numbers of hidden units and (B) large numbers of…

Probability · Mathematics 2019-06-04 Justin Sirignano , Konstantinos Spiliopoulos

Open quantum systems can display periodic dynamics at the classical level either due to external periodic modulations or to self-pulsing phenomena typically following a Hopf bifurcation. In both cases, the quantum fluctuations around…

Quantum Physics · Physics 2021-02-24 C. Navarrete-Benlloch , R. Garcés , N. Mohseni , G. J. de Valcárcel

Due to common architecture designs, symmetries exist extensively in contemporary neural networks. In this work, we unveil the importance of the loss function symmetries in affecting, if not deciding, the learning behavior of machine…

Machine Learning · Computer Science 2024-06-04 Liu Ziyin

Researchers commonly believe that neural networks model a high-dimensional space but cannot give a clear definition of this space. What is this space? What is its dimension? And does it has finite dimensions? In this paper, we develop a…

Machine Learning · Computer Science 2023-05-10 John Chiang

The activity of ensembles of simultaneously recorded neurons can be represented as a set of points in the space of firing rates. Even though the dimension of this space is equal to the ensemble size, neural activity can be effectively…

Neurons and Cognition · Quantitative Biology 2016-03-17 Luca Mazzucato , Alfredo Fontanini , Giancarlo La Camera

A phenomenon known as ''Neural Collapse (NC)'' in deep classification tasks, in which the penultimate-layer features and the final classifiers exhibit an extremely simple geometric structure, has recently attracted considerable attention,…

Machine Learning · Computer Science 2025-11-05 Chuang Ma , Tomoyuki Obuchi , Toshiyuki Tanaka

It is now well established that a high-frequency electromagnetic dressing field within the off-resonance regime significantly modifies the electronic transport and optical properties on Dirac materials. Here, using light with circular…

Mesoscale and Nanoscale Physics · Physics 2024-12-13 Sita Kandel , Godfrey Gumbs , Antonios Balassis , Andrii Iurov , Oleksiy Roslyak

A model of the columnar functional organization of neocortical association areas is studied. The neuronal network is composed of many Hebbian autoassociators, or modules, each of which interacts with a relatively small number of the others.…

Disordered Systems and Neural Networks · Physics 2020-05-14 Carlo Fulvi Mari

In this work it is described how to enhance and generalize the equivalent model (arXiv:0802.0421) of integrate-and-fire dynamics in order to treat any complex neuronal networks, especially those exibiting modular structure. It has been…

Physics and Society · Physics 2008-02-12 Luciano da Fontoura Costa

Optical computing could reduce the energy cost of artificial intelligence by leveraging the parallelism and propagation speed of light. However, implementing nonlinear activation, essential for machine learning, remains challenging in…

Optics · Physics 2026-01-01 Bahadır Utku Kesgin , Gülsüm Yaren Durdu , Uğur Teğin
‹ Prev 1 8 9 10 Next ›