Zobrazeno 1 - 10
of 135
pro vyhledávání: '"Wersing, Heiko"'
Autor:
Sieker, Judith, Junker, Simeon, Utescher, Ronja, Attari, Nazia, Wersing, Heiko, Buschmeier, Hendrik, Zarrieß, Sina
We examine how users perceive the limitations of an AI system when it encounters a task that it cannot perform perfectly and whether providing explanations alongside its answers aids users in constructing an appropriate mental model of the system's c
Externí odkaz:
http://arxiv.org/abs/2406.19170
Autor:
Tanneberg, Daniel, Ocker, Felix, Hasler, Stephan, Deigmoeller, Joerg, Belardinelli, Anna, Wang, Chao, Wersing, Heiko, Sendhoff, Bernhard, Gienger, Michael
How can a robot provide unobtrusive physical support within a group of humans? We present Attentive Support, a novel interaction concept for robots to support a group of humans. It combines scene perception, dialogue acquisition, situation understand
Externí odkaz:
http://arxiv.org/abs/2403.12533
Autor:
Beierling, Helen, Richter, Phillip, Brandt, Mara, Terfloth, Lutz, Schulte, Carsten, Wersing, Heiko, Vollmer, Anna-Lisa
Nowadays, we are dealing more and more with robots and AI in everyday life. However, their behavior is not always apparent to most lay users, especially in error situations. As a result, there can be misconceptions about the behavior of the technolog
Externí odkaz:
http://arxiv.org/abs/2311.14431
Detecting mental states of human users is crucial for the development of cooperative and intelligent robots, as it enables the robot to understand the user's intentions and desires. Despite their importance, it is difficult to obtain a large amount o
Externí odkaz:
http://arxiv.org/abs/2202.03775
Autor:
Beierling, Helen, Richter, Phillip, Brandt, Mara, Terfloth, Lutz, Schulte, Carsten, Wersing, Heiko, Vollmer, Anna-Lisa
Publikováno v:
In Cognitive Systems Research December 2024 88
While Machine learning gives rise to astonishing results in automated systems, it is usually at the cost of large data requirements. This makes many successful algorithms from machine learning unsuitable for human-machine interaction, where the machi
Externí odkaz:
http://arxiv.org/abs/2012.13551
When training automated systems, it has been shown to be beneficial to adapt the representation of data by learning a problem-specific metric. This metric is global. We extend this idea and, for the widely used family of k nearest neighbors algorithm
Externí odkaz:
http://arxiv.org/abs/2011.03904
Deep convolutional neural networks have achieved great successes over recent years, particularly in the domain of computer vision. They are fast, convenient, and -- thanks to mature frameworks -- relatively easy to implement and deploy. However, thei
Externí odkaz:
http://arxiv.org/abs/1910.09239
Publikováno v:
Advances in Intelligent Data Analysis XVIII (2020) Pages 235-247
Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into making any desi
Externí odkaz:
http://arxiv.org/abs/1902.09286
Publikováno v:
In Neurocomputing 22 January 2022 470:344-351