10 citations · 27 across the 10 of their papers we have counts for
9 papers · 1 filter
On the Generalization of PINNs outside the training domain and the Hyperparameters influencing it
Andrea Bonfanti, Roberto Santana, Marco Ellero +1
Physics-Informed Neural Networks (PINNs) are Neural Network architectures trained to emulate solutions of differential equations without the necessity of solution data. They are cu…
When and How to Fool Explainable Models (and Humans) with Adversarial Examples
Jon Vadillo, Roberto Santana, Jose A. Lozano
Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpr…
Analysis of Dominant Classes in Universal Adversarial Perturbations
Jon Vadillo, Roberto Santana, Jose A. Lozano
The reasons why Deep Neural Networks are susceptible to being fooled by adversarial examples remains an open discussion. Indeed, many different strategies can be employed to effici…
Extending Adversarial Attacks to Produce Adversarial Class Probability Distributions
Jon Vadillo, Roberto Santana, Jose A. Lozano
Despite the remarkable performance and generalization levels of deep learning models in a wide range of artificial intelligence tasks, it has been demonstrated that these models ca…
Universal adversarial examples in speech command classification
Jon Vadillo, Roberto Santana
Adversarial examples are inputs intentionally perturbed with the aim of forcing a machine learning model to produce a wrong prediction, while the changes are not easily detectable…
Evolving Gaussian Process kernels from elementary mathematical expressions
Ibai Roman, Roberto Santana, Alexander Mendiburu +1
Choosing the most adequate kernel is crucial in many Machine Learning applications. Gaussian Process is a state-of-the-art technique for regression and classification that heavily…