Hippocampal formation trains independent components via forcing input reconstruction
A. Lõrincz
Proceedings of the ICANN'97, Lausanne,
pp. 163--168
(1997)
Abstract
It is assumed that higher order concept formation utilizes independent components (ICs).
It is argued that ICs require dynamic input reconstruction networks (RNs) to form a reliable internal
reprezentation. Input reconstruction, however, can be slow and poor with ICs on substrates with
lossy dynamics. A model of the hippocampal formation is proposed that develops the ICs on lossy
RNs by means of locking inputs to the internal representation and thus forcing fast reconstruction
and cancelling losses. It is assumed that upon training ICs can lock themeselves, thus hippocampal
lesion mostly affects anterograde memories.
