English
Related papers

Related papers: Fixed width treelike neural networks capacity anal…

200 papers

Deep neural networks are often trained in the over-parametrized regime (i.e. with far more parameters than training examples), and understanding why the training converges to solutions that generalize remains an open problem. Several…

Machine Learning · Statistics 2018-03-23 Hartmut Maennel , Olivier Bousquet , Sylvain Gelly

We present a greedy-based approach to construct an efficient single hidden layer neural network with the ReLU activation that approximates a target function. In our approach we obtain a shallow network by utilizing a greedy algorithm with…

Machine Learning · Computer Science 2021-10-01 Anton Dereventsov , Armenak Petrosyan , Clayton Webster

Deep neural networks with adaptive configurations have gained increasing attention due to the instant and flexible deployment of these models on platforms with different resource budgets. In this paper, we investigate a novel option to…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Qing Jin , Linjie Yang , Zhenyu Liao

Convolutional neural networks (CNNs) with residual links (ResNets) and causal dilated convolutional units have been the network of choice for deep learning approaches to speech enhancement. While residual links improve gradient flow during…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-02 Mohammad Nikzad , Aaron Nicolson , Yongsheng Gao , Jun Zhou , Kuldip K. Paliwal , Fanhua Shang

We study deep neural networks with polynomial activations, particularly their expressive power. For a fixed architecture and activation degree, a polynomial neural network defines an algebraic map from weights to polynomials. The image of…

Machine Learning · Computer Science 2019-05-30 Joe Kileel , Matthew Trager , Joan Bruna

While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1)…

Machine Learning · Computer Science 2019-08-27 Tomaso Poggio , Andrzej Banburski , Qianli Liao

Tree-structured neural networks have proven to be effective in learning semantic representations by exploiting syntactic information. In spite of their success, most existing models suffer from the underfitting problem: they recursively use…

Computation and Language · Computer Science 2017-05-12 Pengfei Liu , Xipeng Qiu , Xuanjing Huang

Deep convolutional neural networks (DCNNs) have shown remarkable performance in image classification tasks in recent years. Generally, deep neural network architectures are stacks consisting of a large number of convolutional layers, and…

Computer Vision and Pattern Recognition · Computer Science 2017-09-07 Dongyoon Han , Jiwhan Kim , Junmo Kim

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate \emph{scaled} ResNet in the limit of infinitely deep and wide…

Machine Learning · Computer Science 2024-03-18 Yihang Chen , Fanghui Liu , Yiping Lu , Grigorios G. Chrysos , Volkan Cevher

We establish convergence of the training dynamics of residual neural networks (ResNets) to their joint infinite depth L, hidden width M, and embedding dimension D limit. Specifically, we consider ResNets with two-layer perceptron blocks in…

Machine Learning · Statistics 2026-03-23 Louis-Pierre Chaintron , Lénaïc Chizat , Javier Maass

Recurrent neural networks (RNNs) are powerful dynamical models, widely used in machine learning (ML) and neuroscience. Prior theoretical work has focused on RNNs with additive interactions. However, gating - i.e. multiplicative -…

Disordered Systems and Neural Networks · Physics 2021-12-02 Kamesh Krishnamurthy , Tankut Can , David J. Schwab

We consider neural networks with rational activation functions. The choice of the nonlinear activation function in deep learning architectures is crucial and heavily impacts the performance of a neural network. We establish optimal bounds…

Neural and Evolutionary Computing · Computer Science 2020-10-01 Nicolas Boullé , Yuji Nakatsukasa , Alex Townsend

We explicitly construct the quantum field theory corresponding to a general class of deep neural networks encompassing both recurrent and feedforward architectures. We first consider the mean-field theory (MFT) obtained as the leading…

High Energy Physics - Theory · Physics 2022-01-27 Kevin T. Grosvenor , Ro Jefferson

Topological methods for comparing weighted graphs are valuable in various learning tasks but often suffer from computational inefficiency on large datasets. We introduce RTD-Lite, a scalable algorithm that efficiently compares topological…

Machine Learning · Computer Science 2025-03-18 Eduard Tulchinskii , Daria Voronkova , Ilya Trofimov , Evgeny Burnaev , Serguei Barannikov

Complex-valued neural networks (CVNNs) have been shown to be powerful nonlinear approximators when the input data can be properly modeled in the complex domain. One of the major challenges in scaling up CVNNs in practice is the design of…

Neural and Evolutionary Computing · Computer Science 2019-02-07 Simone Scardapane , Steven Van Vaerenbergh , Danilo Comminiello , Aurelio Uncini

Recurrent neural networks (RNN) are powerful tools to explain how attractors may emerge from noisy, high-dimensional dynamics. We study here how to learn the ~N^(2) pairwise interactions in a RNN with N neurons to embed L manifolds of…

Disordered Systems and Neural Networks · Physics 2020-02-05 Aldo Battista , Rémi Monasson

Extreme weather events and cyberattacks can cause component failures and disrupt the operation of power distribution networks (DNs), during which reconfiguration and load shedding are often adopted for resilience enhancement. This study…

Systems and Control · Electrical Eng. & Systems 2026-03-10 Roshni Anna Jacob , Prithvi Poddar , Jaidev Goel , Souma Chowdhury , Yulia R. Gel , Jie Zhang

We demonstrate that a very deep ResNet with stacked modules with one neuron per hidden layer and ReLU activation functions can uniformly approximate any Lebesgue integrable function in $d$ dimensions, i.e. $\ell_1(\mathbb{R}^d)$. Because of…

Machine Learning · Computer Science 2018-07-05 Hongzhou Lin , Stefanie Jegelka

Understanding the intricate operations of Recurrent Neural Networks (RNNs) mechanistically is pivotal for advancing their capabilities and applications. In this pursuit, we propose the Episodic Memory Theory (EMT), illustrating that RNNs…

Neural and Evolutionary Computing · Computer Science 2023-10-05 Arjun Karuvally , Peter Delmastro , Hava T. Siegelmann

Beam Tree Recursive Neural Network (BT-RvNN) was recently proposed as a simple extension of Gumbel Tree RvNN and it was shown to achieve state-of-the-art length generalization performance in ListOps while maintaining comparable performance…

Machine Learning · Computer Science 2023-11-09 Jishnu Ray Chowdhury , Cornelia Caragea
‹ Prev 1 8 9 10 Next ›