English
Related papers

Related papers: A unified framework for Hamiltonian deep neural ne…

200 papers

The past few years have witnessed an increased interest in learning Hamiltonian dynamics in deep learning frameworks. As an inductive bias based on physical laws, Hamiltonian dynamics endow neural networks with accurate long-term…

Machine Learning · Computer Science 2022-03-02 Zhijie Chen , Mingquan Feng , Junchi Yan , Hongyuan Zha

We propose Impatient Deep Neural Networks (DNNs) which deal with dynamic time budgets during application. They allow for individual budgets given a priori for each test example and for anytime prediction, i.e., a possible interruption at…

Computer Vision and Pattern Recognition · Computer Science 2016-10-11 Manuel Amthor , Erik Rodner , Joachim Denzler

There has been increasing interest in methodologies that incorporate physics priors into neural network architectures to enhance their modeling capabilities. A family of these methodologies that has gained traction are Hamiltonian neural…

Classical Physics · Physics 2024-12-05 Ignacio Puiggros T. , A. Srikantha Phani

This paper investigates efficient deep neural networks (DNNs) to replace dense unstructured weight matrices with structured ones that possess desired properties. The challenge arises because the optimal weight matrix structure in popular…

Machine Learning · Computer Science 2024-03-11 Changwoo Lee , Hun-Seok Kim

Deep neural networks (DNNs) have shown great success in many machine learning tasks. Their training is challenging since the loss surface of the network architecture is generally non-convex, or even non-smooth. How and under what…

Machine Learning · Computer Science 2022-02-09 Lam M. Nguyen , Trang H. Tran , Marten van Dijk

The rapid growth of research in exploiting machine learning to predict chaotic systems has revived a recent interest in Hamiltonian Neural Networks (HNNs) with physical constraints defined by the Hamilton's equations of motion, which…

Machine Learning · Computer Science 2021-06-02 Chen-Di Han , Bryan Glaz , Mulugeta Haile , Ying-Cheng Lai

Recently, optimal time variable learning in deep neural networks (DNNs) was introduced in arXiv:2204.08528. In this manuscript we extend the concept by introducing a regularization term that directly relates to the time horizon in discrete…

Machine Learning · Computer Science 2023-12-07 Evelyn Herberg , Roland Herzog , Frederik Köhne

By embedding physical intuition, network architectures enforce fundamental properties, such as energy conservation laws, leading to plausible predictions. Yet, scaling these models to intrinsically high-dimensional systems remains a…

Machine Learning · Computer Science 2026-05-14 Katharina Friedl , Noémie Jaquier , Alyx Liao , Danica Kragic

The wireless network is undergoing a trend from "onnection of things" to "connection of intelligence". With data spread over the communication networks and computing capability enhanced on the devices, distributed learning becomes a hot…

Information Theory · Computer Science 2021-08-03 Jian Wang , Yourui Huangfu , Rong Li , Yiqun Ge , Jun Wang

The success of Deep Neural Networks (DNNs) highly depends on data quality. Moreover, predictive uncertainty makes high performing DNNs risky for real-world deployment. In this paper, we aim to address these two issues by proposing a unified…

Machine Learning · Computer Science 2020-09-28 Krishanu Sarker , Xiulong Yang , Yang Li , Saeid Belkasim , Shihao Ji

In this paper, we study Discretized Neural Networks (DNNs) composed of low-precision weights and activations, which suffer from either infinite or zero gradients due to the non-differentiable discrete function during training. Most…

Machine Learning · Computer Science 2024-12-20 Jun Chen , Hanwen Chen , Mengmeng Wang , Guang Dai , Ivor W. Tsang , Yong Liu

Deep neural networks have become invaluable tools for supervised machine learning, e.g., classification of text or images. While often offering superior results over traditional techniques and successfully expressing complicated patterns in…

Machine Learning · Computer Science 2019-02-19 Eldad Haber , Lars Ruthotto

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

Deep neural networks can be fragile and sensitive to small input perturbations that might cause a significant change in the output. In this paper, we employ contraction theory to improve the robustness of neural ODEs (NODEs). A dynamical…

Machine Learning · Computer Science 2022-07-12 Muhammad Zakwan , Liang Xu , Giancarlo Ferrari-Trecate

As a network-based functional approximator, we have proposed a "Lagrangian Density Space-Time Deep Neural Networks" (LDDNN) topology. It is qualified for unsupervised training and learning to predict the dynamics of underlying physical…

Quantum Physics · Physics 2022-07-26 Bhupesh Bishnoi

Deep neural networks (DNNs) have achieved remarkable success across diverse domains, but their performance can be severely degraded by noisy or corrupted training data. Conventional noise mitigation methods often rely on explicit…

Machine Learning · Computer Science 2025-06-16 Deliang Jin , Gang Chen , Shuo Feng , Yufeng Ling , Haoran Zhu

This paper presents a partial differential equation framework for deep residual neural networks and for the associated learning problem. This is done by carrying out the continuum limits of neural networks with respect to width and depth.…

Analysis of PDEs · Mathematics 2020-08-25 Hailiang Liu , Peter Markowich

Learning continuous-time dynamics on complex networks is crucial for understanding, predicting and controlling complex systems in science and engineering. However, this task is very challenging due to the combinatorial complexities in the…

Social and Information Networks · Computer Science 2020-06-19 Chengxi Zang , Fei Wang

The reduction of Hamiltonian systems aims to build smaller reduced models, valid over a certain range of time and parameters, in order to reduce computing time. By maintaining the Hamiltonian structure in the reduced model, certain…

Numerical Analysis · Mathematics 2024-09-17 Raphaël Côte , Emmanuel Franck , Laurent Navoret , Guillaume Steimer , Vincent Vigon

While the depth of modern Convolutional Neural Networks (CNNs) surpasses that of the pioneering networks with a significant margin, the traditional way of appending supervision only over the final classifier and progressively propagating…

Computer Vision and Pattern Recognition · Computer Science 2021-08-23 Duo Li , Qifeng Chen