English
Related papers

Related papers: Depth-Width Trade-offs for Neural Networks via Top…

200 papers

We analyze the expressivity of a universal deep neural network that can be organized as a series of nested qubit rotations, accomplished by adjustable data re-uploads. While the maximal expressive power increases with the depth of the…

Quantum Physics · Physics 2023-11-13 Iván Panadero , Yue Ban , Hilario Espinós , Ricardo Puebla , Jorge Casanova , Erik Torrontegui

The current paradigm of training deep neural networks for classification tasks includes minimizing the empirical risk that pushes the training loss value towards zero, even after the training error has been vanished. In this terminal phase…

Machine Learning · Computer Science 2024-06-07 Hien Dang , Tho Tran , Tan Nguyen , Nhat Ho

In machine learning, there is a fundamental trade-off between ease of optimization and expressive power. Neural Networks, in particular, have enormous expressive power and yet are notoriously challenging to train. The nature of that…

Machine Learning · Computer Science 2015-11-24 Diogo Almeida , Nate Sauder

A key attribute that drives the unprecedented success of modern Recurrent Neural Networks (RNNs) on learning tasks which involve sequential data, is their ability to model intricate long-term temporal dependencies. However, a well…

Machine Learning · Computer Science 2020-03-24 Alon Ziv

Cortical neurons are complex, multi-timescale processors wired into recurrent circuits, shaped by long evolutionary pressure under stringent biological constraints. Mainstream machine learning, by contrast, predominantly builds models from…

Machine Learning · Computer Science 2026-05-13 Aaron Spieler , Georg Martius , Anna Levina

Spatial and temporal resource constraints are critical for both biological and artificial intelligent systems. Here we define differentiable cost terms for breadth, depth, and time within a recurrent convolutional neural network conceived…

Neurons and Cognition · Quantitative Biology 2026-05-26 Eivinas Butkus , Kedar Garzón Gupta , Nikolaus Kriegeskorte

A recurrent neural network (RNN) is a widely used deep-learning network for dealing with sequential data. Imitating a dynamical system, an infinite-width RNN can approximate any open dynamical system in a compact domain. In general, deep…

Machine Learning · Statistics 2023-03-30 Chang hoon Song , Geonho Hwang , Jun ho Lee , Myungjoo Kang

Despite significant advances in the field of deep learning in ap-plications to various areas, an explanation of the learning pro-cess of neural network models remains an important open ques-tion. The purpose of this paper is a comprehensive…

Machine Learning · Computer Science 2023-06-07 German Magai

The benefits of depth in feedforward neural networks are well known: composing multiple layers of linear transformations with nonlinear activations enables complex computations. While similar effects are expected in recurrent neural…

Machine Learning · Computer Science 2026-04-03 Maude Lizaire , Michael Rizvi-Martel , Éric Dupuis , Guillaume Rabusseau

We study the average robustness notion in deep neural networks in (selected) wide and narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in the under-parameterized setting, width has a negative effect…

Machine Learning · Computer Science 2023-02-13 Zhenyu Zhu , Fanghui Liu , Grigorios G Chrysos , Volkan Cevher

In this study, we explore the impact of network topology on the approximation capabilities of artificial neural networks (ANNs), with a particular focus on complex topologies. We propose a novel methodology for constructing complex ANNs…

Neural and Evolutionary Computing · Computer Science 2023-10-24 Tommaso Boccato , Matteo Ferrante , Andrea Duggento , Nicola Toschi

For almost 70 years, researchers have typically selected the width of neural networks' layers either manually or through automated hyperparameter tuning methods such as grid search and, more recently, neural architecture search. This paper…

Machine Learning · Computer Science 2026-02-17 Federico Errica , Henrik Christiansen , Viktor Zaverkin , Mathias Niepert , Francesco Alesiani

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

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

It is well-known that the training of Deep Neural Networks (DNN) can be formalized in the language of optimal control. In this context, this paper leverages classical turnpike properties of optimal control problems to attempt a quantifiable…

Machine Learning · Computer Science 2021-01-11 Timm Faulwasser , Arne-Jens Hempel , Stefan Streif

This paper discovers that the neural network with lower decision boundary (DB) variability has better generalizability. Two new notions, algorithm DB variability and $(\epsilon, \eta)$-data DB variability, are proposed to measure the…

Machine Learning · Computer Science 2023-12-27 Shiye Lei , Fengxiang He , Yancheng Yuan , Dacheng Tao

Neural networks can be thought of as applying a transformation to an input dataset. The way in which they change the topology of such a dataset often holds practical significance for many tasks, particularly those demanding non-homeomorphic…

Machine Learning · Computer Science 2024-06-05 Kosio Beshkov , Gaute T. Einevoll

Constructing the architecture of a neural network is a challenging pursuit for the machine learning community, and the dilemma of whether to go deeper or wider remains a persistent question. This paper explores a comparison between deeper…

Machine Learning · Computer Science 2026-01-21 Yahong Yang , Juncai He

We prove several hardness results for training depth-2 neural networks with the ReLU activation function; these networks are simply weighted sums (that may include negative coefficients) of ReLUs. Our goal is to output a depth-2 neural…

Machine Learning · Computer Science 2020-11-30 Surbhi Goel , Adam Klivans , Pasin Manurangsi , Daniel Reichman

The escalating parameter counts in modern deep learning models pose a fundamental challenge to efficient training and resolution of overfitting. We address this by introducing the \emph{Mapping Networks} which replace the high dimensional…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Lord Sen , Shyamapada Mukherjee
‹ Prev 1 3 4 5 6 7 10 Next ›