LSTM Neural Networks: Input to State Stability and Probabilistic Safety Verification
Abstract
The goal of this paper is to analyze Long Short Term Memory (LSTM) neural networks from a dynamical system perspective. The classical recursive equations describing the evolution of LSTM can be recast in state space form, resulting in a time invariant nonlinear dynamical system. In this work, a sufficient condition guaranteeing the Input-to-State (ISS) stability property of this system are provided. Then, a discussion on the verification of LSTM networks is provided; in particular, a dedicated approach based on the scenario algorithm is devised. The proposed method is eventually tested on a pH neutralization process.
Cite
Text
Bonassi et al. "LSTM Neural Networks: Input to State Stability and Probabilistic Safety Verification." Proceedings of the 2nd Conference on Learning for Dynamics and Control, 2020.Markdown
[Bonassi et al. "LSTM Neural Networks: Input to State Stability and Probabilistic Safety Verification." Proceedings of the 2nd Conference on Learning for Dynamics and Control, 2020.](https://mlanthology.org/l4dc/2020/bonassi2020l4dc-lstm/)BibTeX
@inproceedings{bonassi2020l4dc-lstm,
title = {{LSTM Neural Networks: Input to State Stability and Probabilistic Safety Verification}},
author = {Bonassi, Fabio and Terzi, Enrico and Farina, Marcello and Scattolini, Riccardo},
booktitle = {Proceedings of the 2nd Conference on Learning for Dynamics and Control},
year = {2020},
pages = {85-94},
volume = {120},
url = {https://mlanthology.org/l4dc/2020/bonassi2020l4dc-lstm/}
}