Share This Author
Mitigating Concept Drift via Rejection
- Jan Philip Göpfert, B. Hammer, H. Wersing
- Computer ScienceInternational Conference on Artificial Neural…
- 4 October 2018
Two recent learning architectures for drift are extended, the self-adjusting memory architecture (SAM-kNN) and adaptive random forests (ARF), to incorporate a reject option, resulting in highly competitive state-of-the-art technologies.
Classification of motor errors to provide real-time feedback for sports coaching in virtual reality - A case study in squats and Tai Chi pushes
Adversarial attacks hidden in plain sight
A technique is composed that allows to hide adversarial attacks in regions of high complexity, such that they are imperceptible even to an astute observer with regards to human visual perception.
Deep Learning for Understanding Satellite Imagery: An Experimental Survey
- S. Mohanty, Jakub Czakon, M. Schilling
- Environmental Science, Computer ScienceFrontiers in Artificial Intelligence
- 16 November 2020
Five approaches based on improvements of U-Net and Mask R-Convolutional Neuronal Networks models are presented, coupled with unique training adaptations using boosting algorithms, morphological filter, Conditional Random Fields and custom losses, which demonstrate the feasibility of Deep Learning in automated satellite image annotation.
Interpretation of linear classifiers by means of feature relevance bounds
Ontology-based Extraction of Structured Information from Publications on Preclinical Experiments for Spinal Cord Injury Treatments
A first prototype of an ontology-based information extraction system that automatically extracts relevant preclinical knowledge about spinal cord injury treatments from natural language text by recognizing participating entity classes and linking them to each other is described.
Adversarial Robustness Curves
This work takes first steps towards separating robustness analysis from the choice of robustness threshold and norm, and proposes robustness curves as a more general view of the robustness behavior of a model and investigates under which circumstances they can qualitatively depend on the chosen norm.
Towards an Automatic Analysis of CHO-K1 Suspension Growth in Microfluidic Single-cell Cultivation
- Dominik Stallmann, Jan Philip Göpfert, Julian Schmitz, A. Grünberger, B. Hammer
- Computer Science, BiologyBioinform.
- 20 October 2020
A novel machine learning architecture is proposed together with a specialized training procedure, which allows us to infuse a deep neural network with human-powered abstraction on the level of data, leading to a high-performing regression model that requires only a very small amount of labeled data.
Interpretable Locally Adaptive Nearest Neighbors
Why robots should be technical: Correcting mental models through technical architecture concepts
- L. Hindemith, Anna-Lisa Vollmer, Jan Philip Göpfert, Christiane B. Wiebel-Herboth, B. Wrede
- Computer ScienceArXiv
- 5 November 2020
This work investigates how communicating technical concepts of robotic systems to users affects their mental models, and how this can increase the quality of human-robot interaction, and shows the importance of consciously designing robots that express their capabilities and limitations.