Download PDFOpen PDF in browser

Verification of Continuous Time Recurrent Neural Networks (Benchmark Proposal)

12 pagesPublished: September 17, 2018

Abstract

This manuscript presents a description and implementation of two benchmark problems for continuous-time recurrent neural network (RNN) verification. The first problem deals with the approximation of a vector field for a fixed point attractor located at the origin, whereas the second problem deals with the system identification of a forced damped pendulum. While the verification of neural networks is complicated and often impenetrable to the majority of verification techniques, continuous-time RNNs represent a class of networks that may be accessible to reachability methods for nonlinear ordinary differential equations (ODEs) derived originally in biology and neuroscience. Thus, an understanding of the behavior of a RNN may be gained by simulating the nonlinear equations from a diverse set of initial conditions and inputs, or considering reachability analysis from a set of initial conditions. The verification of continuous-time RNNs is a research area that has received little attention and if the research community can achieve meaningful results in this domain, then this class of neural networks may prove to be a superior approach in solving complex problems compared to other network architectures.

Keyphrases: benchmark, neural networks, reachability analysis, recurrent neural networks, rnns

In: Goran Frehse (editor). ARCH18. 5th International Workshop on Applied Verification of Continuous and Hybrid Systems, vol 54, pages 196-207.

BibTeX entry
@inproceedings{ARCH18:Verification_Continuous_Time_Recurrent,
  author    = {Patrick Musau and Taylor T. Johnson},
  title     = {Verification of Continuous Time Recurrent Neural Networks (Benchmark Proposal)},
  booktitle = {ARCH18. 5th International Workshop on Applied Verification of Continuous and Hybrid Systems},
  editor    = {Goran Frehse},
  series    = {EPiC Series in Computing},
  volume    = {54},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/K6SZ},
  doi       = {10.29007/6czp},
  pages     = {196-207},
  year      = {2018}}
Download PDFOpen PDF in browser