Abstract | ||
---|---|---|
Memory constitutes an essential cognitive capability of humans and animals. It allows them to act in very complex, non-stationary environments. In this paper, we propose a perceptual memory system, which is intended to be applied on a humanoid robot learning affordances. According to the properties of biological memory systems, it has been designed in such a way as to enable life-long learning without catastrophic forgetting. Based on clustering sensory information, a symbolic representation is derived automatically. In contrast to alternative approaches, our memory system does not rely on pre-trained models and works completely unsupervised. |
Year | Venue | Keywords |
---|---|---|
2011 | ICANN (2) | pre-trained model,non-stationary environment,memory system,sensory information,biological memory system,affordance learning,essential cognitive capability,life-long learning,alternative approach,perceptual memory system,humanoid robot |
Field | DocType | Volume |
Cognitive robotics,Forgetting,Computer science,Human–computer interaction,Artificial intelligence,Lifelong learning,Cluster analysis,Cognition,Affordance,Humanoid robot,Computer vision,Perception,Machine learning | Conference | 6792 |
ISSN | Citations | PageRank |
0302-9743 | 2 | 0.37 |
References | Authors | |
13 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marc Kammer | 1 | 8 | 0.82 |
Marko Tscherepanow | 2 | 150 | 10.53 |
Thomas Schack | 3 | 33 | 7.51 |
Yukie Nagai | 4 | 254 | 38.93 |