We have implemented an aspect of learning and memory in the nervous system using analog electronics. Using a simple synaptic circuit we realize networks with Hebbian type adaptati...
The promise of unsupervised learning methods lies in their potential to use vast amounts of unlabeled data to learn complex, highly nonlinear models with millions of free paramete...
High-Level music descriptors are key ingredients for music information retrieval systems. Although there is a long tradition in extracting information from acoustic signals, the f...
Abstract—The classification of sequences requires the combination of information from different time points. In this paper the detection of facial expressions is considered. Exp...
Flexibility and adaptivity are two of the outstanding characteristics of new media and new technologies. These properties allow new methods to provide physically challenged people...