A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
ASAT: Adaptively Scaled Adversarial Training in Time Series
[article]
2021
arXiv
pre-print
Adversarial training is a method for enhancing neural networks to improve the robustness against adversarial examples. Besides the security concerns of potential adversarial examples, adversarial training can also improve the performance of the neural networks, train robust neural networks, and provide interpretability for neural networks. In this work, we take the first step to introduce adversarial training in time series analysis by taking the finance field as an example. Rethinking existing
arXiv:2108.08976v1
fatcat:pvdid3up2fa3hltqdnd6bfu34u