TorchDyn: A Neural Differential Equations Library
Continuous-depth learning has recently emerged as a novel perspective on deep learning, improving performance in tasks related to dynamical systems and density estimation. Core to these approaches is the neural differential equation, whose forward passes are the solutions of an initial value problem parametrized by a neural network. Unlocking the full potential of continuous-depth models requires a different set of software tools, due to peculiar differences compared to standard discrete neural networks, e.g inference must be carried out via numerical solvers. We introduce TorchDyn, a PyTorch library dedicated to continuous-depth learning, designed to elevate neural differential equations to be as accessible as regular plug-and-play deep learning primitives. This objective is achieved by identifying and subdividing different variants into common essential components, which can be combined and freely repurposed to obtain complex compositional architectures. TorchDyn further offers step-by-step tutorials and benchmarks designed to guide researchers and contributors.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningDensity EstimationSimilar Papers 제목 키워드 기반
DiffEqFlux.jl - A Julia Library for Neural Differential Equations
DiffEqFlux.jl is a library for fusing neural networks and differential equations. In this work we describe differential equations from the viewpoint of data science and discuss the complementary nature between machine le…
BIG-bench Machine LearningSODAs: Sparse Optimization for the Discovery of Differential and Algebraic Equations
Differential-algebraic equations (DAEs) integrate ordinary differential equations (ODEs) with algebraic constraints, providing a fundamental framework for developing models of dynamical systems characterized by timescale…
Model DiscoveryPinnDE: Physics-Informed Neural Networks for Solving Differential Equations
In recent years the study of deep learning for solving differential equations has grown substantially. The use of physics-informed neural networks (PINNs) and deep operator networks (DeepONets) have emerged as two of the…
Time-Series Forecasting, Knowledge Distillation, and Refinement within a Multimodal PDE Foundation Model
Symbolic encoding has been used in multi-operator learning as a way to embed additional information for distinct time-series data. For spatiotemporal systems described by time-dependent partial differential equations, th…
Knowledge DistillationOperator learningTime SeriesTime Series ForecastingSneak Preview: PowerDynamics.jl -= An Open-Source library for analyzing dynamic stability in power grids with high shares of renewable energy
PowerDynamics.jl is an Open-Source library for dynamic power grid modeling built in the latest scientific programming language, Julia. It provides all the tools necessary to analyze the dynamical stability of power grids…