English
Related papers

Related papers: Exponential expressivity in deep neural networks t…

200 papers

This work focuses on deriving quantitative approximation error bounds for neural ordinary differential equations having at most quadratic nonlinearities in the dynamics. The simple dynamics of this model form demonstrates how expressivity…

Machine Learning · Computer Science 2025-06-16 Joshua Hanson , Maxim Raginsky

Batch Normalization (BN) has proven to be an effective algorithm for deep neural network training by normalizing the input to each neuron and reducing the internal covariate shift. The space of weight vectors in the BN layer can be…

Machine Learning · Computer Science 2017-11-01 Minhyung Cho , Jaehyung Lee

Understanding how deep neural networks learn remains a fundamental challenge in modern machine learning. A growing body of evidence suggests that training dynamics undergo a distinct phase transition, yet our understanding of this…

Machine Learning · Computer Science 2025-05-21 Zhanpeng Zhou , Yongyi Yang , Mahito Sugiyama , Junchi Yan

Brains process information through the collective dynamics of large neural networks. Collective chaos was suggested to underlie the complex ongoing dynamics observed in cerebral cortical circuits and determine the impact and processing of…

Chaotic Dynamics · Physics 2020-06-04 Rainer Engelken , Fred Wolf , L. F. Abbott

We study the large-width asymptotics of random fully connected neural networks with weights drawn from $\alpha$-stable distributions, a family of heavy-tailed distributions arising as the limiting distributions in the Gnedenko-Kolmogorov…

Statistics Theory · Mathematics 2025-03-12 Tomás Soto

The impressive expressive power of deep neural networks (DNNs) underlies their widespread applicability. However, while the theoretical capacity of deep architectures is high, the practical expressive power achieved through successful…

Machine Learning · Computer Science 2023-12-21 Zezhong Zhang , Feng Bao , Guannan Zhang

Diffusion is a key element of a large set of phenomena occurring on natural and social systems modeled in terms of complex weighted networks. Here, we introduce a general formalism that allows to easily write down mean-field equations for…

Statistical Mechanics · Physics 2010-07-14 Andrea Baronchelli , Romualdo Pastor-Satorras

Algorithm unfolding or unrolling is the technique of constructing a deep neural network (DNN) from an iterative algorithm. Unrolled DNNs often provide better interpretability and superior empirical performance over standard DNNs in signal…

Machine Learning · Statistics 2024-02-21 Carter Lyons , Raghu G. Raj , Margaret Cheney

Many learning problems involve symmetries, and while invariance can be built into neural architectures, it can also emerge implicitly when training on group-structured data. We study this phenomenon in classical Hopfield networks and show…

Machine Learning · Computer Science 2026-01-21 Michael Murray , Tenzin Chan , Kedar Karhadker , Christopher J. Hillar

In this work, we build a generic architecture of Convolutional Neural Networks to discover empirical properties of neural networks. Our first contribution is to introduce a state-of-the-art framework that depends upon few hyper parameters…

Computer Vision and Pattern Recognition · Computer Science 2017-03-07 Edouard Oyallon

Training deep neural networks results in strong learned representations that show good generalization capabilities. In most cases, training involves iterative modification of all weights inside the network via back-propagation. In Extreme…

Machine Learning · Computer Science 2018-02-06 Amir Rosenfeld , John K. Tsotsos

The infinitely wide neural network has been proven a useful and manageable mathematical model that enables the understanding of many phenomena appearing in deep learning. One example is the convergence of random deep networks to Gaussian…

Machine Learning · Statistics 2024-03-19 Thiziri Nait-Saada , Alireza Naderi , Jared Tanner

Deep neural networks (DNNs) have emerged as a popular mathematical tool for function approximation due to their capability of modelling highly nonlinear functions. Their applications range from image classification and natural language…

Machine Learning · Computer Science 2019-12-30 SiQi Zhou , Angela P. Schoellig

This paper proves an abstract theorem addressing in a unified manner two important problems in function approximation: avoiding curse of dimensionality and estimating the degree of approximation for out-of-sample extension in manifold…

Machine Learning · Computer Science 2019-11-05 Hrushikesh N. Mhaskar

Graph diffusion models have made significant progress in learning structured graph data and have demonstrated strong potential for predictive tasks. Existing approaches typically embed node, edge, and graph-level features into a unified…

Machine Learning · Computer Science 2025-12-12 Yisen Gao , Xingcheng Fu , Qingyun Sun , Jianxin Li , Xianxian Li

Motivated by applications in chemistry and other sciences, we study the expressive power of message-passing neural networks for geometric graphs, whose node features correspond to 3-dimensional positions. Recent work has shown that such…

Machine Learning · Computer Science 2025-02-18 Yonatan Sverdlov , Nadav Dym

This article studies the infinite-width limit of deep feedforward neural networks whose weights are dependent, and modelled via a mixture of Gaussian distributions. Each hidden node of the network is assigned a nonnegative random variable…

Machine Learning · Statistics 2025-02-06 Hoil Lee , Fadhel Ayed , Paul Jung , Juho Lee , Hongseok Yang , François Caron

The paper characterizes classes of functions for which deep learning can be exponentially better than shallow learning. Deep convolutional networks are a special case of these conditions, though weight sharing is not the main reason for…

Machine Learning · Computer Science 2017-02-07 Tomaso Poggio , Hrushikesh Mhaskar , Lorenzo Rosasco , Brando Miranda , Qianli Liao

Random projections are able to perform dimension reduction efficiently for datasets with nonlinear low-dimensional structures. One well-known example is that random matrices embed sparse vectors into a low-dimensional subspace nearly…

Machine Learning · Computer Science 2019-01-11 Jian-Feng Cai , Dong Li , Jiaze Sun , Ke Wang

A recent paradigm views deep neural networks as discretizations of certain controlled ordinary differential equations, sometimes called neural ordinary differential equations. We make use of this perspective to link expressiveness of deep…

Optimization and Control · Mathematics 2020-07-20 Christa Cuchiero , Martin Larsson , Josef Teichmann
‹ Prev 1 8 9 10 Next ›