Verification of recurrent neural networks for cognitive tasks via reachability analysis

H Zhang
H Zhang
Maxwell Shinn
Maxwell Shinn
Aarti Gupta
Aarti Gupta
Arie Gurfinkel
Arie Gurfinkel
Nham Le
Nham Le

ECAI, pp. 1690-1697, 2020.

Cited by: 0|Bibtex|Views3|DOI:https://doi.org/10.3233/FAIA200281
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com

Abstract:

Recurrent Neural Networks (RNNs) are one of the most successful neural network architectures that deal with temporal sequences, eg, speech and text recognition. Recently, RNNs have been shown to be useful in cognitive neuroscience as a model of decisionmaking. RNNs can be trained to solve the same behavioral tasks performed by humans and ...More

Code:

Data:

Your rating :
0

 

Tags
Comments