Learning Logic Program Representation for Delayed Systems With Limited Training Data

Abstract : Understanding the influences between components of dynamical systems such as biological networks, cellular automata or social networks provides insights to their dynamics. Influences of such dynamical systems can be represented by logic programs with delays. Logical methods that learn logic programs from observations have been developed, but their practical use is limited since they cannot handle noisy input and need a huge amount of data to give accurate results. In this paper , we present a method that learns to distinguish different dynamical systems with delays based on Recurrent Neural Network (RNN). This method relies on Long Short-Term Memory (LSTM) to extract and encode features from input sequences of time series data. We show that the produced high dimensional encoding can be used to distinguish different dynamical systems and reproduce their specific behaviors.
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01766236
Contributor : Tony Ribeiro <>
Submitted on : Friday, April 13, 2018 - 1:56:40 PM
Last modification on : Tuesday, April 2, 2019 - 1:47:07 AM

File

ILP_2017_paper_60.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons CC0 - Public Domain Dedication 4.0 International License

Identifiers

  • HAL Id : hal-01766236, version 1

Collections

Citation

Yin Phua, Tony Ribeiro, Sophie Tourret, Katsumi Inoue. Learning Logic Program Representation for Delayed Systems With Limited Training Data. the 27th International Conference on Inductive Logic Programming, Sep 2017, Orléans, France. ⟨hal-01766236⟩

Share

Metrics

Record views

529

Files downloads

62