Explicit construction of recurrent neural networks effectively approximating discrete dynamical systems

2024/09/28 by Chikara Nakayama, Nakayama, Chikara, Tsuyoshi Yoneda +1
Computer Science · Physics and Astronomy · #Dynamical Systems (math.DS) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Model Reduction and Neural Networks #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2409.19278

openalex publication_date 2024/09/28 · openalex created_date 2024/10/28 · openalex updated_date 2026/07/28

Abstract

We consider arbitrary bounded discrete time series originating from dynamical system with recursivity. More precisely, we provide an explicit construction of recurrent neural networks which effectively approximate the corresponding discrete dynamical systems.

Related

• Transformation of ReLU-based recurrent neural networks from discrete-time to continuous-time
• Synthesis of recurrent neural networks for dynamical system simulation
• Universal approximation of flows of control systems by recurrent neural networks
• Liquid Time-constant Recurrent Neural Networks as Universal Approximators
• Metric Entropy Limits on Recurrent Neural Network Learning of Linear Dynamical Systems