Research | LAMARR

For professionals: Our authors report research trends and their current scientific work on Machine Learning.

|Darstellung der Shapley-Werte zur Erklärung von Merkmalen der Eingabedaten. Die Gatter nehmen dabei die Position von „Spielern“ in einem Koalitionsspiel ein.|Modifizierte Quantenschaltung zur Bestimmung der Beitrag der einzelnen Gatter.

Explaining Gates in Quantum Circuits with Shapley Values

May 23rd, 2023

Sascha

Mücke

By applying Shapley values to quantum computing, Lamarr scientists seek to explain the role of specific gates in a quantum circuit and give insights into how quantum machine learning models work.

View Post

ChatGPT: Has a chatbot finally achieved self-awareness?

February 10th, 2023

Christian

Bauckhage

Is ChatGPT aware of itself? In this article, our author Prof. Dr. Christian Bauckhage actively looks for signs of consciousness.

View Post

ChatGPT: How smart is the hyped chatbot?

February 3rd, 2023

Christian

Bauckhage

How smart is ChatGPT and can it learn from its mistakes? Our author talked some more with the chatbot and put it through an intelligence test.

View Post

ChatGPT: An assessment of the polarizing chatbot

January 27th, 2023

Christian

Bauckhage

ChatGPT has been a buzzword since its release. In this series, Prof. Dr. Christian Bauckhage takes a closer look at this hype and shares his own experiences.

View Post

|Zuckerrübenfeld in Bonn|Bild des Zuckerrübenfeldes aus Bonn wird übersetzt

Autonomous robots for agriculture 4.0

October 19th, 2022

Cyrill

Stachniss

PhenoRob

Webmaster

Agriculture is fundamental to ensure our livelihood. Autonomous robots that can monitor, understand and act on fields have the potential to assist in sustainable agriculture 4.0.

View Post

00_Blog_Jakobs_Wissenschaftliches-Arbeiten-leicht-gemacht

Research Made Easy: Efficient literature study

June 13th, 2022

Matthias

Jakobs

Self-organization is an important skill in many industries. This is especially the case in research, where multiple projects often need to be managed without predetermined tasks. The process of researching a topic in particular has the potential to be an endless task. To streamline this process, we present some tricks and tools in this article. […]

View Post

An Approach to Granular Testing of Deep Neural Networks

June 1st, 2022

Sujan Sai

Gannamaneni

Establishing rigorous testing and certification techniques is essential before deploying new technologies like Deep Learning (DL) in safety-critical applications. We propose a testing approach that could identify weaknesses in DL models.

View Post

An Explainability Method for Point Clouds

May 4th, 2022

Hanxiao

Tan

A surrogate model-based explainability approach is proposed for point cloud classifiers together with two different evaluation metrics validating the plausibility of the approach. The toolkit is now available online.

View Post

ART – Automated Tool for Generating Financial Statements

March 16th, 2022

Rafet

Sifa

Creating financial reports takes a lot of time and is expensive. ART is a new method that should make it possible to convert structured table data from financial reports into text.

View Post