Kai-Uwe Kühnberger

Kai-Uwe Kühnberger

Auto-generated profile, based on publicly available information

Kai-Uwe Kühnberger

Osnabrück University

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 March 2006 in Theoretical Computer Science
Verified
Journal Article
Closed access
HGHelmar Gust
Helmar Gust
KKKai-Uwe Kühnberger
Kai-Uwe Kühnberger
USUte Schmid
Ute Schmid

1 October 2005 in Studia Logica
Verified
Journal Article
Closed access
PDF file
KKKai-Uwe Küdhnberger
Kai-Uwe Küdhnberger
BLBenedikt Löwe
Benedikt Löwe
MMMichael Möllerfeld
Michael Möllerfeld
PWPhilip Welch
Philip Welch

1 February 2021 in Neural Networks
Verified
Journal Article
Open access
VCViviane Clay
Viviane Clay
Peter KönigPeter König
Peter König
KKKai-Uwe Kühnberger
Kai-Uwe Kühnberger
GPGordon Pipa
Gordon Pipa
How do humans acquire a meaningful understanding of the world with little to no supervision or semantic labels provided by the environment? Here we investigate embodiment with a closed loop between action and perception as one key component in this process. We take a close look at the representations learned by a deep reinforcement learning agent that is trained with high-dimensional visual observations collected in a 3D environment with very sparse rewards. We show that this agent learns stable representations of meaningful concepts such as doors without receiving any semantic labels. Our results show that the agent learns to represent the action relevant information, extracted from a simulated camera stream, in a wide variety of sparse activation patterns. The quality of the representations learned shows the strength of embodied learning and its advantages over fully supervised approaches.

10 November 2017 in arXiv
Verified
Preprint
Open access
PDF file
TBTarek R. Besold
Tarek R. Besold
AGArtur D'Avila Garcez
Artur D'Avila Garcez
SBSebastian Bader
Sebastian Bader
HBHoward Bowman
Howard Bowman
PDPedro Domingos
Pedro Domingos
GZGerson Zaverucha
Gerson Zaverucha
The study and understanding of human behaviour is relevant to computer science, artificial intelligence, neural computation, cognitive science, philosophy, psychology, and several other areas. Presupposing cognition as basis of behaviour, among the most prominent tools in the modelling of behaviour are computational-logic systems, connectionist models of cognition, and models of uncertainty. Recent studies in cognitive science, artificial intelligence, and psychology have produced a number of cognitive models of reasoning, learning, and language that are underpinned by computation. In addition, efforts in computer science research have led to the development of cognitive computational systems integrating machine learning and automated reasoning. Such systems have shown promise in a range of applications, including computational biology, fault diagnosis, training and assessment in simulators, and software verification. This joint survey reviews the personal ideas and views of several researchers on neural-symbolic learning and reasoning. The article is organised in three parts: Firstly, we frame the scope and goals of neural-symbolic computation and have a look at the theoretical foundations. We then proceed to describe the realisations of neural-symbolic computation, systems, and applications. Finally we present the challenges facing the area and avenues for further research.

13 April 2016 in Annals of Mathematics and Artificial Intelligence
Verified
Journal Article
Closed access
PDF file
MMM. Martinez
M. Martinez
Ahmed M. H. ABDELFATTAHAhmed M. H. ABDELFATTAH
Ahmed M. H. ABDELFATTAH
UKU. Krumnack
U. Krumnack
DGD. Gómez-Ramírez
D. Gómez-Ramírez
ASA. Smaill
A. Smaill
KKK.-U. Kühnberger
K.-U. Kühnberger

9 October 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
VCViviane Clay
Viviane Clay
GPGordon Pipa
Gordon Pipa
KKKai-Uwe Kühnberger
Kai-Uwe Kühnberger
Peter KönigPeter König
Peter König
Most artificial neural networks used for object recognition are trained in a fully supervised setup. This is not only resource consuming as it requires large data sets of labeled examples but also quite different from how humans learn. We use a setup in which an artificial agent first learns in a simulated world through self-supervised, curiosity-driven exploration. Following this initial learning phase, the learned representations can be used to quickly associate semantic concepts such as different types of doors using one or more labeled examples. To do this, we use a method we call fast concept mapping which uses correlated firing patterns of neurons to define and detect semantic concepts. This association works instantaneously with very few labeled examples, similar to what we observe in humans in a phenomenon called fast mapping . Strikingly, we can already identify objects with as little as one labeled example which highlights the quality of the encoding learned self-supervised through interaction with the world. It therefore presents a feasible strategy for learning concepts without much supervision and shows that through pure interaction meaningful representations of an environment can be learned that work better for few-short learning than non-interactive methods.