Path sampling of recurrent neural networks by incorporating known physics

Abstract

Recurrent neural networks have seen widespread use in modeling dynamical systems in varied domains such as weather prediction, text prediction and several others. Often one wishes to supplement the experimentally observed dynamics with prior knowledge or intuition about the system. While the recurrent nature of these networks allows them to model arbitrarily long memories in the time series used in training, it makes it harder to impose prior knowledge or intuition through generic constraints. In this work, we present a path sampling approach based on principle of Maximum Caliber that allows us to include generic thermodynamic or kinetic constraints into recurrent neural networks. We show the method here for a widely used type of recurrent neural network known as long short-term memory network in the context of supplementing time series collected from different application domains. These include classical Molecular Dynamics of a protein and Monte Carlo simulations of an open quantum system continuously losing photons to the environment and displaying Rabi oscillations. Our method can be easily generalized to other generative artificial intelligence models and to generic time series in different areas of physical and social sciences, where one wishes to supplement limited data with intuition or theory based corrections.

arXiv commentAdded results for open quantum system with dissipative photon dynamics

References in corpus (16)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Double-slit photoelectron interference in strong-field ionization of the neon dimer
• QuTiP: An open-source Python framework for the dynamics of open quantum systems
• A short introduction to the Lindblad Master Equation
• Dynamics on the Way to Forming Glass: Bubbles in Space-time
• Thermodynamics of Quantum Jump Trajectories
• Data-Driven Collective Variables for Enhanced Sampling
• Neural networks-based variationally enhanced sampling
• Neural network based path collective variables for enhanced sampling of phase transformations
• Learning Molecular Dynamics with Simple Language Model built upon Long Short-Term Memory Neural Network
• Making rare events typical in Markovian open quantum systems
• Maximum Caliber: a general variational principle for dynamical systems
• A simple derivation of the Lindblad equation
• Predicting reaction coordinates in energy landscapes with diffusion anisotropy
• Markov processes follow from the principle of Maximum Caliber
• Studying rare nonadiabatic dynamics with transition path sampling quantum jump trajectories

Cited by in corpus (2)

• Deep learning for dynamic modeling and coded information storage of vector-soliton pulsations in mode-locked fiber lasers
• Density Matrix Emulation of Quantum Recurrent Neural Networks for Multivariate Time Series Prediction