Abstract.
A new self-organizing map (SOM) architecture called the ASSOM (adaptive-subspace SOM) is shown to create sets of translation-invariant filters when randomly displaced or moving input patterns are used as training data. No analytical functional forms for these filters are thereby postulated. Different kinds of filters are formed by the ASSOM when pictures are rotated during learning, or when they are zoomed. The ASSOM can thus act as a learning feature-extraction stage for pattern recognizers, being able to adapt to many sensory environments and to many different transformation groups of patterns.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
Received: 14 September 1995 / Accepted in revised form: 8 May 1996
Rights and permissions
About this article
Cite this article
Kohonen, T. Emergence of invariant-feature detectors in the adaptive-subspace self-organizing map. Biol Cybern 75, 281–291 (1996). https://doi.org/10.1007/s004220050295
Issue Date:
DOI: https://doi.org/10.1007/s004220050295