English
Related papers

Related papers: Neural networks for learning macroscopic chemotact…

200 papers

Prediction of molecular properties, including physico-chemical properties, is a challenging task in chemistry. Herein we present a new state-of-the-art multitask prediction method based on existing graph neural network models. We have used…

Machine Learning · Computer Science 2019-10-31 Fabio Capela , Vincent Nouchi , Ruud Van Deursen , Igor V. Tetko , Guillaume Godin

We consider Markov models of large-scale networks where nodes are characterized by their local behavior and by a mobility model over a two-dimensional lattice. By assuming random walk, we prove convergence to a system of partial…

Networking and Internet Architecture · Computer Science 2016-04-27 Max Tschaikowski , Mirco Tribastone

Intracellular transport processes are essential to the healthy development of many organisms as well as more generally to healthy cellular function. The complex dynamics and interactions between protein molecules and filaments on different…

Dynamical Systems · Mathematics 2022-07-27 Maria-Veronica Ciocanel

Pathophysiolpgical modelling of brain systems from microscale to macroscale remains difficult in group comparisons partly because of the infeasibility of modelling the interactions of thousands of neurons at the scales involved. Here, to…

Neurons and Cognition · Quantitative Biology 2026-01-30 Kang You , Gary Green , Jian Zhang

A stochastic walker model is proposed to describe the chemotactic guidance of growth cones, i.e. the tips of developing neurites. The model accounts for the influence of both attractive and repulsive chemical cues, which are emitted by the…

Analysis of PDEs · Mathematics 2025-11-04 Noah Geltner , Ansgar Jüngel

We propose a novel method to train deep convolutional neural networks which learn from multiple data sets of varying input sizes through weight sharing. This is an advantage in chemometrics where individual measurements represent exact…

Machine Learning · Statistics 2019-11-11 Jacob Søgaard Larsen , Line Clemmensen

The data-driven discovery of partial differential equations (PDEs) consistent with spatiotemporal data is experiencing a rebirth in machine learning research. Training deep neural networks to learn such data-driven partial differential…

Numerical Analysis · Mathematics 2020-11-10 Hassan Arbabi , Judith E. Bunder , Giovanni Samaey , Anthony J. Roberts , Ioannis G. Kevrekidis

The classical macroscopic chemotaxis equations have previously been derived from an individual-based description of the tactic response of cells that use a "run-and-tumble" strategy in response to environmental cues. Here we derive…

Cell Behavior · Quantitative Biology 2007-05-23 Radek Erban , Hans G. Othmer

One of the main questions regarding complex systems at large scales concerns the effective interactions and driving forces that emerge from the detailed microscopic properties. Coarse-grained models aim to describe complex systems in terms…

Computational Physics · Physics 2022-12-21 Elham Kiyani , Steven Silber , Mahdi Kooshkbaghi , Mikko Karttunen

Recent years have witnessed a growth in mathematics for deep learning--which seeks a deeper understanding of the concepts of deep learning with mathematics and explores how to make it more robust--and deep learning for mathematics, where…

Machine Learning · Computer Science 2023-10-31 Derick Nganyu Tanyu , Jianfeng Ning , Tom Freudenberg , Nick Heilenkötter , Andreas Rademacher , Uwe Iben , Peter Maass

There have been growing interests in leveraging experimental measurements to discover the underlying partial differential equations (PDEs) that govern complex physical phenomena. Although past research attempts have achieved great success…

Machine Learning · Computer Science 2023-05-23 Chengping Rao , Pu Ren , Yang Liu , Hao Sun

We introduce mesoscopic and macroscopic model equations of chemotaxis with anomalous subdiffusion for modelling chemically directed transport of biological organisms in changing chemical environments with diffusion hindered by traps or…

Dynamical Systems · Mathematics 2012-12-03 T. A. M. Langlands , B. I. Henry

Dosing models often use differential equations to model biological dynamics. Neural differential equations in particular can learn to predict the derivative of a process, which permits predictions at irregular points of time. However, this…

Machine Learning · Computer Science 2023-06-27 Stav Belogolovsky , Ido Greenberg , Danny Eytan , Shie Mannor

Macroscopic dynamical descriptions of complex physical systems are crucial for understanding and controlling material behavior. With the growing availability of data and compute, machine learning has become a promising alternative to…

Computational Physics · Physics 2026-03-24 Mengyi Chen , Pengru Huang , Kostya S. Novoselov , Qianxiao Li

The machine learning methods for data-driven identification of partial differential equations (PDEs) are typically defined for a given number of spatial dimensions and a choice of coordinates the data have been collected in. This dependence…

Machine Learning · Computer Science 2025-10-07 Trung V. Phan , George A. Kevrekidis , Soledad Villar , Yannis G. Kevrekidis , Juan M. Bello-Rivas

Nonlinear partial differential equations (PDEs) are used to model dynamical processes in a large number of scientific fields, ranging from finance to biology. In many applications standard local models are not sufficient to accurately…

Numerical Analysis · Mathematics 2022-05-10 Victor Boussange , Sebastian Becker , Arnulf Jentzen , Benno Kuckuck , Loïc Pellissier

It has been shown experimentally that contact interactions may influence the migration of cancer cells. Previous works have modelized this thanks to stochastic, discrete models (cellular automata) at the cell level. However, for the study…

Cell Behavior · Quantitative Biology 2009-03-26 Christophe Deroulers , Marine Aubert , Mathilde Badoual , Basil Grammaticos

When solving partial differential equations (PDEs), classical numerical methods often require fine mesh grids and small time stepping to meet stability, consistency, and convergence conditions, leading to high computational cost. Recently,…

Approximate solutions of partial differential equations (PDEs) obtained by neural networks are highly affected by hyper parameter settings. For instance, the model training strongly depends on loss function design, including the choice of…

Numerical Analysis · Mathematics 2025-03-13 Hee Jun Yang , Alexander Heinlein , Hyea Hyun Kim

Dynamical systems theory provides powerful methods to extract effective macroscopic dynamics from complex systems with slow modes and fast modes. Here we derive and theoretically support a macroscopic, spatially discrete, model for a class…

Analysis of PDEs · Mathematics 2010-03-12 Wei Wang , A. J. Roberts