Home2021-04-09T09:47:22+00:00

Analytics is
more than just
statistics.

Empower your decisions with modern AI that understands all your data.

Learn more
Contact Us

Analytics is
more than just
statistics.

Empower your decisions with modern AI that understands all your data.

Learn more
Contact Us

Analytics is
more than just
statistics.

Empower your decisions with modern AI that understands all your data.

Learn more
Contact Us

Services

We accompany you on your way from the first attempts with AI prototypes to the productive use of AI solutions within your regular infrastructure.

Learn more

Technology

We deal with the technical and non-technical facets of AI and prepare you for the topics of tomorrow.

Learn more

Technology

Federated Learning

How AI can be trained successfully and in compliance with data protection regulations through Federated Learning.

Learn more

Contact Us

Not all important information
are in tables.

Make use of what is in the texts and graphics of your reports. Contact us!

Contact Us

Not all important information
are in tables.

Make use of what is in the texts and graphics of your reports. Contact us!

Up-and-coming: Fairness in Natural Language Processing

April 6, 2021|

Fairness is a central aspect of the ethically responsible development and application of Artificial Intelligence. Because humans may be biased, so may be Machine Learning (ML) models trained on data that reflects human biases.

Briefly noted: Backdoors in Federated Learning

March 9, 2021|

In their NeurIPS-2020 article, Wang et al. discuss the injection of backdoors into a model during model training. In an FL setting, the goal of a backdoor is to corrupt the global (federated) model such that it mispredicts on a targeted sub-task.

To the blog

Briefly noted: Gender Bias Occupies a Linear Subspace

Gender bias is the most studied fairness issue in Natural Language Processing. In their recent EMNLP-2020 article, Vargas & Cotterell show that within word embedding space, gender bias occupies a linear subspace.

Up-and-coming: Fairness in Natural Language Processing

Fairness is a central aspect of the ethically responsible development and application of Artificial Intelligence. Because humans may be biased, so may be Machine Learning (ML) models trained on data that reflects human biases.

Briefly noted: Backdoors in Federated Learning

In their NeurIPS-2020 article, Wang et al. discuss the injection of backdoors into a model during model training. In an FL setting, the goal of a backdoor is to corrupt the global (federated) model such that it mispredicts on a targeted sub-task.

To the blog
Go to Top