Differentiable Programming of Reaction-Diffusion Patterns

• URL: http://arxiv.org/abs/2107.06862v1
• Date: Tue, 22 Jun 2021 17:38:34 GMT
• Title: Differentiable Programming of Reaction-Diffusion Patterns
• Authors: Alexander Mordvintsev, Ettore Randazzo, Eyvind Niklasson
• Abstract summary: We propose a differentiable optimization method for learning the RD system parameters to perform example-based texture synthesis on a 2D plane. We do this by representing the RD system as a variant of Neural Cellular Automata and using task-specific differentiable loss functions.
• Score: 64.70093734012121
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Reaction-Diffusion (RD) systems provide a computational framework that governs many pattern formation processes in nature. Current RD system design practices boil down to trial-and-error parameter search. We propose a differentiable optimization method for learning the RD system parameters to perform example-based texture synthesis on a 2D plane. We do this by representing the RD system as a variant of Neural Cellular Automata and using task-specific differentiable loss functions. RD systems generated by our method exhibit robust, non-trivial 'life-like' behavior.

Related papers

• Generative Learning of the Solution of Parametric Partial Differential Equations Using Guided Diffusion Models and Virtual Observations [4.798951413107239]
  We introduce a generative learning framework to model high-dimensional parametric systems. We consider systems described by Partial Differential Equations (PDEs) discretized with structured or unstructured grids.
  arXiv  Detail & Related papers  (2024-07-31T20:52:33Z)
• On the Trajectory Regularity of ODE-based Diffusion Sampling [79.17334230868693]
  Diffusion-based generative models use differential equations to establish a smooth connection between a complex data distribution and a tractable prior distribution. In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models.
  arXiv  Detail & Related papers  (2024-05-18T15:59:41Z)
• Learning minimal representations of stochastic processes with variational autoencoders [52.99137594502433]
  We introduce an unsupervised machine learning approach to determine the minimal set of parameters required to describe a process. Our approach enables for the autonomous discovery of unknown parameters describing processes.
  arXiv  Detail & Related papers  (2023-07-21T14:25:06Z)
• A Constructive Approach to Function Realization by Neural Stochastic Differential Equations [8.04975023021212]
  We introduce structural restrictions on system dynamics and characterize the class of functions that can be realized by such a system. The systems are implemented as a cascade interconnection of a neural differential equation (Neural SDE), a deterministic dynamical system, and a readout map.
  arXiv  Detail & Related papers  (2023-07-01T03:44:46Z)
• Parameter Identification for Partial Differential Equations with Spatiotemporal Varying Coefficients [5.373009527854677]
  We propose a framework that facilitates the investigation of parameter identification for multi-state systems governed by varying partial differential equations. Our framework consists of two integral components: a constrained self-adaptive neural network, and a sub-network physics-informed neural network. We have showcased the efficacy of our framework on two numerical cases: the 1D Burgers' cases with time-varying parameters and the 2 wave equation with a space-varying parameter.
  arXiv  Detail & Related papers  (2023-06-30T07:17:19Z)
• Learning the Delay Using Neural Delay Differential Equations [0.5505013339790825]
  We develop a continuous time neural network approach based on Delay Differential Equations (DDEs) Our model uses the adjoint sensitivity method to learn the model parameters and delay directly from data. We conclude our discussion with potential future directions and applications.
  arXiv  Detail & Related papers  (2023-04-03T19:50:36Z)
• Design of Turing Systems with Physics-Informed Neural Networks [0.0]
  We investigate the use of physics-informed neural networks as a tool to infer key parameters in reaction-diffusion systems. Our proof-of-concept results show that the method is able to infer parameters for different pattern modes and types with errors of less than 10%.
  arXiv  Detail & Related papers  (2022-11-24T08:01:22Z)
• RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation [110.4255414234771]
  Existing solutions require massive training data or lack generalizability to unknown rendering configurations. We propose a novel approach that marries domain randomization and differentiable rendering gradients to address this problem. Our approach achieves significantly lower reconstruction errors and has better generalizability among unknown rendering configurations.
  arXiv  Detail & Related papers  (2022-05-11T17:59:51Z)
• Learning Linearized Assignment Flows for Image Labeling [70.540936204654]
  We introduce a novel algorithm for estimating optimal parameters of linearized assignment flows for image labeling. We show how to efficiently evaluate this formula using a Krylov subspace and a low-rank approximation.
  arXiv  Detail & Related papers  (2021-08-02T13:38:09Z)
• Ensemble and Random Collaborative Representation-Based Anomaly Detector for Hyperspectral Imagery [133.83048723991462]
  We propose a novel ensemble and random collaborative representation-based detector (ERCRD) for hyperspectral anomaly detection (HAD) Our experiments on four real hyperspectral datasets exhibit the accuracy and efficiency of this proposed ERCRD method compared with ten state-of-the-art HAD methods.
  arXiv  Detail & Related papers  (2021-01-06T11:23:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.