SOM’s and GSOM’s in biologically inspired models of speech processing

Abstract:

Modeling speech processing in a biologically inspired way can be done by using growing self-organizing maps. But this approach is highly abstract because each “node” here represents an ensemble of “real” neurons, in our interpretation a cortical column. Moreover neural spikes trains are not modeled in this approach. Rather a mean rate of neural activation is taken as basic processing variable for each node. In this paper the concept of growing self-organized maps is reviewed and its neuroscientific relevance is discussed (i) from the viewpoint of spatial and temporal integration (cortical columns and activity rates) and (ii) from the viewpoint of basic neural principles like self-organization and associative learning in speech processing.


Year: 2014
In session: Sprachtherapie: Grundlagen und Anwendungen
Pages: 142 to 147