Guided Reinforcement Learning describes a concept for learning control policies of intelligent robots. By incorporating additional knowledge, the training process becomes more data-efficient and effective for real-world robotics.
Two different approaches to point cloud interpretability are proposed, which elucidate the properties of the model from global and model-internal perspectives, respectively. All toolkits are now available on GitHub.
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.
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.
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.
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. […]
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.