TopoART: A topology learning hierarchical ART network
M Tscherepanow - International Conference on Artificial Neural Networks, 2010 - Springer
In this paper, a novel unsupervised neural network combining elements from Adaptive
Resonance Theory and topology learning neural networks, in particular the Self-Organising …
Resonance Theory and topology learning neural networks, in particular the Self-Organising …
A hierarchical ART network for the stable incremental learning of topological structures and associations from noisy data
M Tscherepanow, M Kortkamp, M Kammer - Neural Networks, 2011 - Elsevier
In this article, a novel unsupervised neural network combining elements from Adaptive
Resonance Theory and topology-learning neural networks is presented. It enables stable on …
Resonance Theory and topology-learning neural networks is presented. It enables stable on …
Interactive incremental online learning of objects onboard of a cooperative autonomous mobile robot
Detecting objects and referring to them in a dialog is a crucial requirement for robotic
systems that cooperate with humans. For this, in an unrestricted natural environment the …
systems that cooperate with humans. For this, in an unrestricted natural environment the …
Teaching human poses interactively to a social robot
The main activity of social robots is to interact with people. In order to do that, the robot must
be able to understand what the user is saying or doing. Typically, this capability consists of …
be able to understand what the user is saying or doing. Typically, this capability consists of …
[인용][C] Developmental robotics: From babies to robots
A Cangelosi, M Schlesinger - 2015 - MIT press
Learning information acquisition for multitasking scenarios in dynamic environments
Real world environments are so dynamic and unpredictable that a goal-oriented
autonomous system performing a set of tasks repeatedly never experiences the same …
autonomous system performing a set of tasks repeatedly never experiences the same …
Reward-based learning of optimal cue integration in audio and visual depth estimation
Many real-world applications in robotics have to deal with imprecisions and noise when
using only a single information source for computation. Therefore making use of additional …
using only a single information source for computation. Therefore making use of additional …
An analysis of depth estimation within interaction range
Interactions between humans or humanoids and their environment through tasks like
gras** or manipulation typically require accurate depth information. The human vision …
gras** or manipulation typically require accurate depth information. The human vision …
Intelligent system architectures-comparison by translation
B Dittes, C Goerick - 2011 IEEE/RSJ International Conference …, 2011 - ieeexplore.ieee.org
System architectures are a central element to enable construction of increasingly complex
software systems for intelligent artifacts. Scientific discourse about such architectures …
software systems for intelligent artifacts. Scientific discourse about such architectures …
Optimisation of gaze movement for multitasking using rewards
Domestic tasks such as gras** or navigation for robotic systems can be supported by
vision. However, the environment provides a vast amount of visual information and …
vision. However, the environment provides a vast amount of visual information and …