Understanding recurrent neural networks using nonequilibrium response theory
From MaRDI portal
Publication:4998938
Recommendations
- Distributed sequence memory of multidimensional inputs in recurrent networks
- Opening the black box: low-dimensional dynamics in high-dimensional recurrent neural networks
- A Geometrical Analysis of Global Stability in Trained Feedback Networks
- Stimulus-Driven and Spontaneous Dynamics in Excitatory-Inhibitory Recurrent Neural Networks for Sequence Representation
- Metric entropy limits on recurrent neural network learning of linear dynamical systems
Cites work
- A course on rough paths. With an introduction to regularity structures
- A proposal on machine learning via dynamical systems
- A simple framework to justify linear response theory
- A Unifying View of Wiener and Volterra Theory and Polynomial Kernel Regression
- Adaptive Euler-Maruyama method for SDEs with nonglobally Lipschitz drift
- An update on the nonequilibrium linear response
- Analytical Foundations of Volterra Series
- Bayesian learning for neural networks
- Chen's iterated integral represents the operator product expansion
- Deep learning
- Deep learning as optimal control problems: models and numerical methods
- Dynamical systems as temporal feature spaces
- Echo state networks are universal
- Fading memory and the problem of approximating nonlinear operators with Volterra series
- Fluctuation relations for diffusion processes
- Fonctionnelles causales non linéaires et indéterminées non commutatives
- Formal Theory of Nonlinear Response
- Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network
- scientific article; zbMATH DE number 1804115 (Why is no real title available?)
- scientific article; zbMATH DE number 3140813 (Why is no real title available?)
- scientific article; zbMATH DE number 5689708 (Why is no real title available?)
- scientific article; zbMATH DE number 3989703 (Why is no real title available?)
- scientific article; zbMATH DE number 54145 (Why is no real title available?)
- scientific article; zbMATH DE number 192908 (Why is no real title available?)
- scientific article; zbMATH DE number 1268810 (Why is no real title available?)
- scientific article; zbMATH DE number 221690 (Why is no real title available?)
- scientific article; zbMATH DE number 3802489 (Why is no real title available?)
- scientific article; zbMATH DE number 3261539 (Why is no real title available?)
- Iterated integrals in quantum field theory
- Iterated path integrals
- Kernel methods in machine learning
- Kernels for sequentially ordered data
- Linear response in neuronal networks: From neurons dynamics to collective response
- Machine learning from a continuous viewpoint. I
- Markovian perturbation, response and fluctuation dissipation theorem
- Mathematical foundation of nonequilibrium fluctuation-dissipation theorems for inhomogeneous diffusion processes with unbounded coefficients
- Multidimensional stochastic processes as rough paths. Theory and applications.
- Neurons with graded response have collective computational properties like those of two-state neurons
- Nonlinear dynamical systems and classical orthogonal polynomials
- Nonlinear System Identification Based on a Fock Space Framework
- Optimal Hölder regularity for nonautonomous Kolmogorov equations
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
- Regularization networks and support vector machines
- Reservoir computing approaches to recurrent neural network training
- Rough paths, signatures and the modelling of functions on streams
- Stable architectures for deep neural networks
- Stochastic processes and applications. Diffusion processes, the Fokker-Planck and Langevin equations
- Stochastic training of residual networks in deep learning
- Support Vector Machines
- Symmetric Hilbert spaces and related topics. Infinitely divisible positive definite functions, continuous products and tensor products, Gaussian and Poissonian stochastic processes
- System Control and Rough Paths
- Temporal-kernel recurrent neural networks
- The Koopman operator in systems and control. Concepts, methodologies and applications
- Understanding recurrent neural networks using nonequilibrium response theory
- Uniform approximation by entire functions
- Uniform factorial decay estimates for controlled differential equations
- Volterra series and geometric control theory
Cited in
(10)- \(p\)-adic statistical field theory and deep belief networks
- Understanding recurrent neural networks using nonequilibrium response theory
- Unified field theoretical approach to deep and recurrent neuronal networks
- scientific article; zbMATH DE number 7625195 (Why is no real title available?)
- Differential Geometry Methods for Constructing Manifold-Targeted Recurrent Neural Networks
- Dynamical behavior of recurrent neural networks with different external inputs
- Exploring weight initialization, diversity of solutions, and degradation in recurrent neural networks trained for temporal and decision-making tasks
- Understanding Recurrent Neural Networks Using Nonequilibrium Response Theory
- Response theory identifies reaction coordinates and explains critical phenomena in noisy interacting systems
- Linear RNNs provably learn linear dynamical systems
Describes a project that uses
Uses Software
This page was built for publication: Understanding recurrent neural networks using nonequilibrium response theory
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4998938)
