Machine learning in Madrid

Lunes, 14 de noviembre de 2022, 12-13h
Aula Naranja - ICMAT

Ponente:  Tobias Wöhrer (TU Munich)

Título:    Robustness of neural ODEs - a second order adjoint equation approach

Abstract: We consider augmented training of ODE based neural networks, such as ResNets, to increase robustness with respect to adversarial attacks. This is done by adding a first order sensitivity term to the loss function, derived from the corresponding robust optimal control problem. To reduce memory cost of the training process, we take an optimize then discretize approach and compute the gradients via solving the adjoint sensitivity equation, which is of second order due to the modified loss function. Based on this approach, we will discuss numerical simulations that provide a better intuition for the robustification process.

Enlace:    la charla será retransmitida también por zoom, el enlace será enviado próximamente

Lunes, 14 de noviembre de 2022, 12-13h
Aula Naranja - ICMAT

Ponente:  Tobias Wöhrer (TU Munich)

Título:    Robustness of neural ODEs - a second order adjoint equation approach

Abstract: We consider augmented training of ODE based neural networks, such as ResNets, to increase robustness with respect to adversarial attacks. This is done by adding a first order sensitivity term to the loss function, derived from the corresponding robust optimal control problem. To reduce memory cost of the training process, we take an optimize then discretize approach and compute the gradients via solving the adjoint sensitivity equation, which is of second order due to the modified loss function. Based on this approach, we will discuss numerical simulations that provide a better intuition for the robustification process.

Enlace:    la charla será retransmitida también por zoom, el enlace será enviado próximamente