Analytical comparison of the Temporal Kohonen Map and the Recurrent Self Organizing Map.
Markus Varsta, Jukka Heikkonen, Jouko Lampinen · 2000
The basic SOM is indifferent to the ordering of the input patterns. Real data, however, is often sequential in nature thus context of a pattern may signicantly influence its correct interpretation. One simple SOM model that takes the context of a pattern into account is the Temporal Kohonen Map (TKM), which was modied into the Recurrent Self Organizing Map (RSOM). We show analytically and with experiments that the RSOM is a significant improvement over the TKM because the RSOM model allows simple derivation of a consistent update rule.