rockpool.training.adversarial_jaxο
Functions to implement adversarial training approaches using Jax
See also
πΉ Adversarial training illustrates how to use the functions in this module to implement adversarial attacks on the parameters of a network during training.
Functions
|
Implement a hybrid task / adversarial robustness loss |
|
Performs the PGA (projected gradient ascent) based attack on the parameters of the network given inputs. |