English
Related papers

Related papers: Weight-Parameterization in Continuous Time Deep Ne…

200 papers

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

Neural ODEs (NODEs) have emerged as powerful tools for modeling time series data, offering the flexibility to adapt to varying input scales and capture complex dynamics. However, they face significant challenges: first, their reliance on…

Machine Learning · Computer Science 2025-10-07 Muhao Guo , Yang Weng

Numerical solving parameterised partial differential equations (P-PDEs) is highly practical yet computationally expensive, driving the development of reduced-order models (ROMs). Recently, methods that combine latent space identification…

Machine Learning · Computer Science 2024-10-08 Xinlei Lin , Dunhui Xiao

Residual neural networks are state-of-the-art deep learning models. Their continuous-depth analog, neural ordinary differential equations (ODEs), are also widely used. Despite their success, the link between the discrete and continuous…

Machine Learning · Statistics 2024-07-08 Pierre Marion , Yu-Han Wu , Michael E. Sander , Gérard Biau

Neural differential equations offer a powerful approach for learning dynamics from data. However, they do not impose known constraints that should be obeyed by the learned model. It is well-known that enforcing constraints in surrogate…

Areas of computational mechanics such as uncertainty quantification and optimization usually involve repeated evaluation of numerical models that represent the behavior of engineering systems. In the case of complex nonlinear systems…

Machine Learning · Computer Science 2024-10-03 A. O. M. Kilicsoy , J. Liedmann , M. A. Valdebenito , F. -J. Barthold , M. G. R. Faes

In this paper, we propose the nonlinearity generation method to speed up and stabilize the training of deep convolutional neural networks. The proposed method modifies a family of activation functions as nonlinearity generators (NGs). NGs…

Machine Learning · Computer Science 2017-10-18 Yang Jiang , Zeyang Dou , Qun Hao , Jie Cao , Kun Gao , Xi Chen

Neural operators have emerged as powerful surrogates for the solution of partial differential equations (PDEs), yet their ability to handle general, highly variable boundary conditions (BCs) remains limited. Existing approaches often fail…

Machine Learning · Computer Science 2026-05-14 Sepehr Mousavi , Siddhartha Mishra , Laura De Lorenzis

Deploying deep learning models, comprising of non-linear combination of millions, even billions, of parameters is challenging given the memory, power and compute constraints of the real world. This situation has led to research into model…

Machine Learning · Computer Science 2020-05-29 Muhammad A. Shah , Raphael Olivier , Bhiksha Raj

Continuous neural representations have recently emerged as a powerful and flexible alternative to classical discretized representations of signals. However, training them to capture fine details in multi-scale signals is difficult and…

Machine Learning · Computer Science 2022-10-06 Sifan Wang , Hanwen Wang , Jacob H. Seidman , Paris Perdikaris

Differential equations are widely used to describe complex dynamical systems with evolving parameters in nature and engineering. Effectively learning a family of maps from the parameter function to the system dynamics is of great…

Machine Learning · Computer Science 2025-03-12 Xin Li , Chengli Zhao , Xue Zhang , Xiaojun Duan

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

Deep learning uses neural networks which are parameterised by their weights. The neural networks are usually trained by tuning the weights to directly minimise a given loss function. In this paper we propose to re-parameterise the weights…

Neural and Evolutionary Computing · Computer Science 2022-03-14 Michael Fairbank , Spyridon Samothrakis , Luca Citi

We propose heavy ball neural ordinary differential equations (HBNODEs), leveraging the continuous limit of the classical momentum accelerated gradient descent, to improve neural ODEs (NODEs) training and inference. HBNODEs have two…

Machine Learning · Computer Science 2021-10-12 Hedi Xia , Vai Suliafu , Hangjie Ji , Tan M. Nguyen , Andrea L. Bertozzi , Stanley J. Osher , Bao Wang

Continuous-depth neural networks, such as Neural ODEs, have refashioned the understanding of residual neural networks in terms of non-linear vector-valued optimal control problems. The common solution is to use the adjoint sensitivity…

Machine Learning · Computer Science 2022-02-16 Andrew Corbett , Dmitry Kangin

Solving time-dependent Partial Differential Equations (PDEs) using a densely discretized spatial domain is a fundamental problem in various scientific and engineering disciplines, including modeling climate phenomena and fluid dynamics.…

Machine Learning · Computer Science 2025-10-24 Jan Hagnberger , Daniel Musekamp , Mathias Niepert

Loss of plasticity, trainability loss, and primacy bias have been identified as issues arising when training deep neural networks on sequences of tasks -- all referring to the increased difficulty in training on new tasks. We propose to use…

Machine Learning · Computer Science 2024-12-11 Wesley Chung , Lynn Cherif , David Meger , Doina Precup

Transformer models are increasingly used for solving Partial Differential Equations (PDEs). Several adaptations have been proposed, all of which suffer from the typical problems of Transformers, such as quadratic memory and time complexity.…

Machine Learning · Computer Science 2024-07-16 Jan Hagnberger , Marimuthu Kalimuthu , Daniel Musekamp , Mathias Niepert

We present a novel approach for training deep neural networks in a Bayesian way. Classical, i.e. non-Bayesian, deep learning has two major drawbacks both originating from the fact that network parameters are considered to be deterministic.…

Machine Learning · Statistics 2019-03-11 Konstantin Posch , Jan Steinbrener , Jürgen Pilz

This papers studies the expressive and computational power of discrete Ordinary Differential Equations (ODEs). It presents a new framework using discrete ODEs as a central tool for computation and provides several implicit characterizations…

Logic in Computer Science · Computer Science 2018-10-09 Olivier Bournez , Arnaud Durand , Sabrina Ouazzani
‹ Prev 1 8 9 10 Next ›