English
Related papers

Related papers: Minimal Width for Universal Property of Deep RNN

200 papers

We introduce MinimalRNN, a new recurrent neural network architecture that achieves comparable performance as the popular gated RNNs with a simplified structure. It employs minimal updates within RNN, which not only leads to efficient…

Machine Learning · Statistics 2018-06-21 Minmin Chen

Deep neural networks with rectified linear units (ReLU) are getting more and more popular due to their universal representation power and successful applications. Some theoretical progress regarding the approximation power of deep ReLU…

Numerical Analysis · Mathematics 2020-02-28 Bo Li , Shanshan Tang , Haijun Yu

We contribute to a better understanding of the class of functions that can be represented by a neural network with ReLU activations and a given architecture. Using techniques from mixed-integer optimization, polyhedral theory, and tropical…

Machine Learning · Computer Science 2024-07-18 Christoph Hertrich , Amitabh Basu , Marco Di Summa , Martin Skutella

This survey provides an in-depth and explanatory review of the approximation properties of deep neural networks, with a focus on feed-forward and residual architectures. The primary objective is to examine how effectively neural networks…

Machine Learning · Computer Science 2024-12-18 Owen Davis , Mohammad Motamed

Deep unfolding methods---for example, the learned iterative shrinkage thresholding algorithm (LISTA)---design deep neural networks as learned variations of optimization methods. These networks have been shown to achieve faster convergence…

Machine Learning · Computer Science 2020-03-19 Huynh Van Luong , Boris Joukovsky , Nikos Deligiannis

Recent works have shown that gradient descent can find a global minimum for over-parameterized neural networks where the widths of all the hidden layers scale polynomially with $N$ ($N$ being the number of training samples). In this paper,…

Machine Learning · Computer Science 2020-12-21 Quynh Nguyen , Marco Mondelli

We show that there is a simple (approximately radial) function on $\reals^d$, expressible by a small 3-layer feedforward neural networks, which cannot be approximated by any 2-layer network, to more than a certain constant accuracy, unless…

Machine Learning · Computer Science 2016-05-10 Ronen Eldan , Ohad Shamir

We consider deep neural networks with a Lipschitz continuous activation function and with weight matrices of variable widths. We establish a uniform convergence analysis framework in which sufficient conditions on weight matrices and bias…

Machine Learning · Computer Science 2023-06-05 Yuesheng Xu , Haizhang Zhang

The empirical emergence of neural collapse -- a surprising symmetry in the feature representations of the training data in the penultimate layer of deep neural networks -- has spurred a line of theoretical research aimed at its…

Machine Learning · Computer Science 2025-05-22 Peter Súkeník , Christoph H. Lampert , Marco Mondelli

Recurrent Neural Networks (RNNs) have been widely applied to sequential data analysis. Due to their complicated modeling structures, however, the theory behind is still largely missing. To connect theory and practice, we study the…

Machine Learning · Computer Science 2019-11-05 Minshuo Chen , Xingguo Li , Tuo Zhao

Recurrent neural networks are a powerful means to cope with time series. We show how autoregressive linear, i.e., linearly activated recurrent neural networks (LRNNs) can approximate any time-dependent function f(t). The approximation can…

Machine Learning · Computer Science 2025-10-01 Frieder Stolzenburg , Sandra Litz , Olivia Michael , Oliver Obst

In recent years, deep neural networks (DNNs) achieved unprecedented performance in many low-level vision tasks. However, state-of-the-art results are typically achieved by very deep networks, which can reach tens of layers with tens of…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Idan Kligvasser , Tamar Rott Shaham , Tomer Michaeli

In this paper, we prove that a shallow neural network with a monotone sigmoid, ReLU, ELU, Softplus, or LeakyReLU activation function can arbitrarily well approximate any L^p(p>=2) integrable functions defined on R*[0,1]^n. We also prove…

Machine Learning · Computer Science 2021-10-12 Ming-Xi Wang , Yang Qu

Learning to predict solutions to real-valued combinatorial graph problems promises efficient approximations. As demonstrated based on the NP-hard edge clique cover number, recurrent neural networks (RNNs) are particularly suited for this…

Machine Learning · Statistics 2019-11-20 Nil-Jana Akpinar , Bernhard Kratzwald , Stefan Feuerriegel

Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition. Some of the properties that make RNNs suitable for such tasks, for example robustness to…

Artificial Intelligence · Computer Science 2007-05-23 Alex Graves , Santiago Fernandez , Juergen Schmidhuber

Deep neural networks (DNNs) have garnered significant attention in various fields of science and technology in recent years. Activation functions define how neurons in DNNs process incoming signals for them. They are essential for learning…

Machine Learning · Computer Science 2023-08-31 Jianfei Li , Han Feng , Ding-Xuan Zhou

This paper investigates the universal approximation capabilities of Hamiltonian Deep Neural Networks (HDNNs) that arise from the discretization of Hamiltonian Neural Ordinary Differential Equations. Recently, it has been shown that HDNNs…

Machine Learning · Computer Science 2023-05-31 Muhammad Zakwan , Massimiliano d'Angelo , Giancarlo Ferrari-Trecate

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

A Random Vector Functional Link (RVFL) network is a depth-2 neural network with random inner weights and biases. Only the outer weights of such an architecture are to be learned, so the learning process boils down to a linear optimization…

Machine Learning · Statistics 2025-06-26 Palina Salanevich , Olov Schavemaker

This paper investigates the approximation power of three types of random neural networks: (a) infinite width networks, with weights following an arbitrary distribution; (b) finite width networks obtained by subsampling the preceding…

Machine Learning · Computer Science 2019-10-21 Bolton Bailey , Ziwei Ji , Matus Telgarsky , Ruicheng Xian