Synthesis of recurrent neural networks for dynamical system simulation
We review several of the most widely used techniques for training recurrent neural networks to approximate dynamical systems, then describe a novel algorithm for this task. The algorithm is based on an earlier theoretical result that guarantees the quality of the network approximation. We show that a feedforward neural network can be trained on the vector field representation of a given dynamical system using backpropagation, then recast, using matrix manipulations, as a recurrent network that replicates the original system's dynamics. After detailing this algorithm and its relation to earlier approaches, we present numerical examples that demonstrate its capabilities. One of the distinguishing features of our approach is that both the original dynamical systems and the recurrent networks that simulate them operate in continuous time.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Universal Simulation of Stable Dynamical Systems by Recurrent Neural Nets
It is well-known that continuous-time recurrent neural nets are universal approximators for continuous-time dynamical systems. However, existing results provide approximation guarantees only for finite-time trajectories.…
Synthesis of Stabilizing Recurrent Equilibrium Network Controllers
We propose a parameterization of a nonlinear dynamic controller based on the recurrent equilibrium network, a generalization of the recurrent neural network. We derive constraints on the parameterization under which the …
Policy Gradient MethodsShort note on the behavior of recurrent neural network for noisy dynamical system
The behavior of recurrent neural network for the data-driven simulation of noisy dynamical systems is studied by training a set of Long Short-Term Memory Networks (LSTM) on the Mackey-Glass time series with a wide range …
Time SeriesTime Series AnalysisRecurrent Neural Network-based Internal Model Control design for stable nonlinear systems
Owing to their superior modeling capabilities, gated Recurrent Neural Networks, such as Gated Recurrent Units (GRUs) and Long Short-Term Memory networks (LSTMs), have become popular tools for learning dynamical systems. …
Neural Integration of Continuous Dynamics
Neural dynamical systems are dynamical systems that are described at least in part by neural networks. The class of continuous-time neural dynamical systems must, however, be numerically integrated for simulation and lea…
Numerical Integration