michaelaerni

DataCleaner

The premier open source Data Quality solution

infoseclab_23

misleading-privacy-evals

Official code for "Evaluations of Machine Learning Privacy Defenses are Misleading" (https://arxiv.org/abs/2404.17399)

adversarial_spatial

Investigating the robustness of state-of-the-art CNN architectures to simple spatial transformations.

asdfghjkl

ASDL: Automatic Second-order Differentiation (for Fisher, Gradient covariance, Hessian, Jacobian, and Kernel) Library

comgr

FHNW comgr course project

ether

Java 3D / Media Processing Library

iclr23-InductiveBiasesHarmlessInterpolation

Official repository for the paper "Strong inductive biases provably prevent harmless interpolation"

interpolation_robustness

Code for the paper "Interpolation can hurt robust generalization even when there is no noise" available here: https://papers.nips.cc/paper/2021/hash/c4f2c88e16a579900657c18726641c81-Abstract.html

ip6-molanet

Source code of the "Biomedical Image Segmentation using Generative Adversarial Networks" bachelor thesis by Michael Aerni and Patrick Del Conte.

michaelaerni/interpolation_robustness

Code for the paper "Interpolation can hurt robust generalization even when there is no noise" available here: https://papers.nips.cc/paper/2021/hash/c4f2c88e16a579900657c18726641c81-Abstract.html

michaelaerni/adversarial_spatial

Investigating the robustness of state-of-the-art CNN architectures to simple spatial transformations.

michaelaerni/asdfghjkl

ASDL: Automatic Second-order Differentiation (for Fisher, Gradient covariance, Hessian, Jacobian, and Kernel) Library

michaelaerni/comgr

FHNW comgr course project

michaelaerni/ether

Java 3D / Media Processing Library

michaelaerni/iclr23-InductiveBiasesHarmlessInterpolation

Official repository for the paper "Strong inductive biases provably prevent harmless interpolation"

michaelaerni/ip6-molanet

Source code of the "Biomedical Image Segmentation using Generative Adversarial Networks" bachelor thesis by Michael Aerni and Patrick Del Conte.