English
Related papers

Related papers: On the failure of ReLU activation for physics-info…

200 papers

Gradient descent (GD) type optimization schemes are the standard instruments to train fully connected feedforward artificial neural networks (ANNs) with rectified linear unit (ReLU) activation and can be considered as temporal…

Optimization and Control · Mathematics 2022-02-24 Shokhrukh Ibragimov , Arnulf Jentzen , Timo Kröger , Adrian Riekert

Several recent works in scientific machine learning have revived interest in the application of neural networks to partial differential equations (PDEs). A popular approach is to aggregate the residual form of the governing PDE and its…

Machine Learning · Computer Science 2023-09-13 Shamsulhaq Basir , Inanc Senocak

We show that the error achievable using physics-informed neural networks for solving systems of differential equations can be substantially reduced when these networks are trained using meta-learned optimization methods rather than to using…

Machine Learning · Computer Science 2023-03-15 Alex Bihlo

In this paper, it is demonstrated through a case study that multilayer feedforward neural networks activated by ReLU functions can in principle be trained iteratively with Mixed Integer Linear Programs (MILPs) as follows. Weights are…

Machine Learning · Computer Science 2021-04-12 Steffen Goebbels

We study the properties of differentiable neural networks activated by rectified power unit (RePU) functions. We show that the partial derivatives of RePU neural networks can be represented by RePUs mixed-activated networks and derive upper…

Machine Learning · Statistics 2024-04-23 Guohao Shen , Yuling Jiao , Yuanyuan Lin , Jian Huang

In this paper, we investigate the applications of operator learning, specifically DeepONet, for solving nonlinear partial differential equations (PDEs). Unlike conventional function learning methods that require training separate neural…

Machine Learning · Computer Science 2025-09-30 Yahong Yang

Neural architectures tend to fit their data with relatively simple functions. This "simplicity bias" is widely regarded as key to their success. This paper explores the limits of this principle. Building on recent findings that the…

Machine Learning · Computer Science 2025-03-14 Damien Teney , Liangze Jiang , Florin Gogianu , Ehsan Abbasnejad

Appropriate weight initialization settings, along with the ReLU activation function, have become cornerstones of modern deep learning, enabling the training and deployment of highly effective and efficient neural network models across…

Machine Learning · Computer Science 2024-04-02 Hyunwoo Lee , Yunho Kim , Seung Yeop Yang , Hayoung Choi

We perform an exploratory study of a new approach for evaluating Feynman integrals numerically. We apply the recently-proposed framework of physics-informed deep learning to train neural networks to approximate the solution to the…

High Energy Physics - Phenomenology · Physics 2024-07-24 Francesco Calisto , Ryan Moodie , Simone Zoia

Differential equations are used to model and predict the behaviour of complex systems in a wide range of fields, and the ability to solve them is an important asset for understanding and predicting the behaviour of these systems.…

Machine Learning · Computer Science 2023-01-31 Siddharth Nand , Yuecheng Cai

This study introduces a novel activation function, characterized by a dynamic slope that adjusts throughout the training process, aimed at enhancing adaptability and performance in deep neural networks for computer vision tasks. The…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Archisman Chakraborti , Bidyut B Chaudhuri

We investigate the implications of removing bias in ReLU networks regarding their expressivity and learning dynamics. We first show that two-layer bias-free ReLU networks have limited expressivity: the only odd function two-layer bias-free…

Machine Learning · Computer Science 2025-04-29 Yedi Zhang , Andrew Saxe , Peter E. Latham

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

Sparse computation offers a compelling solution for the inference of Large Language Models (LLMs) in low-resource scenarios by dynamically skipping the computation of inactive neurons. While traditional approaches focus on ReLU-based LLMs,…

Machine Learning · Computer Science 2024-02-07 Zhengyan Zhang , Yixin Song , Guanghui Yu , Xu Han , Yankai Lin , Chaojun Xiao , Chenyang Song , Zhiyuan Liu , Zeyu Mi , Maosong Sun

This paper investigates the ability of finite samples to identify two-layer irreducible shallow networks with various nonlinear activation functions, including rectified linear units (ReLU) and analytic functions such as the logistic…

Machine Learning · Computer Science 2025-03-18 Yu Xia , Zhiqiang Xu

It is difficult to describe in mathematical terms what a neural network trained on data represents. On the other hand, there is a growing mathematical understanding of what neural networks are in principle capable of representing.…

Machine Learning · Computer Science 2025-06-25 Daan Huybrechs

Despite the remarkable success of deep multi-modal learning in practice, it has not been well-explained in theory. Recently, it has been observed that the best uni-modal network outperforms the jointly trained multi-modal network, which is…

Machine Learning · Computer Science 2022-03-24 Yu Huang , Junyang Lin , Chang Zhou , Hongxia Yang , Longbo Huang

Although for neural networks with locally Lipschitz continuous activation functions the classical derivative exists almost everywhere, the standard chain rule is in general not applicable. We will consider a way of introducing a derivative…

Machine Learning · Computer Science 2020-11-12 Julius Berner , Dennis Elbrächter , Philipp Grohs , Arnulf Jentzen

Optimizing parameters with momentum, normalizing data values, and using rectified linear units (ReLUs) are popular choices in neural network (NN) regression. Although ReLUs are popular, they can collapse to a constant function and "die",…

Machine Learning · Computer Science 2020-05-14 Isac Arnekvist , J. Frederico Carvalho , Danica Kragic , Johannes A. Stork

Physics-informed machine learning typically integrates physical priors into the learning process by minimizing a loss function that includes both a data-driven term and a partial differential equation (PDE) regularization. Building on the…

Machine Learning · Statistics 2025-09-23 Nathan Doumèche , Francis Bach , Gérard Biau , Claire Boyer