Show Reference: "A Recurrent Self-Organizing Map for Temporal Sequence Processing"

A Recurrent Self-Organizing Map for Temporal Sequence Processing In Artificial Neural Networks — ICANN'97, Vol. 1327 (1997), pp. 421-426, doi:10.1007/bfb0020191 by Markus Varstal, Josédel R. Millán, Jukka Heikkonen edited by Wulfram Gerstner, Alain Germond, Martin Hasler, Jean-Daniel Nicoud
    abstract = {This paper presents a recurrent self-organizing map ({RSOM}) for temporal sequence processing. The {RSOM} uses the history of a pattern (i.e., the previous elements in the sequence) to compute the best matching unit and to adapt the weights of the map. The {RSOM} is similar to Kohonen's original {SOM} except that each unit has an associated recursive differential equation. The experimental results show that the {RSOM} is able to learn and distinguish temporal sequences, and that it can improve {EEG}-based epileptic activity detection.},
    author = {Varstal, Markus and Mill\'{a}n, Jos\'{e}del R. and Heikkonen, Jukka},
    booktitle = {Artificial Neural Networks — ICANN'97},
    doi = {10.1007/bfb0020191},
    editor = {Gerstner, Wulfram and Germond, Alain and Hasler, Martin and Nicoud, Jean-Daniel},
    keywords = {learning, som, time-series, unsupervised-learning},
    pages = {421--426},
    posted-at = {2013-01-14 11:22:34},
    priority = {2},
    publisher = {Springer Berlin Heidelberg},
    series = {Lecture Notes in Computer Science},
    title = {A Recurrent {Self-Organizing} Map for Temporal Sequence Processing},
    url = {},
    volume = {1327},
    year = {1997}

See the CiteULike entry for more info, PDF links, BibTex etc.

Recursive and Recurrent SOMs have been used for mapping temporal data.