Abstract
We stipulate that the following three categories of dynamic phenomena must be present in a realistic neural-network model: (i) activation; (ii) adaptation; (iii) plasticity control.
In most neural models only activation and adaptation are present. The self-organising map (SOM) algorithm is the only neural-network model that includes all the three phenomena. Its modelling laws include the following partial functions: (1) Some parallel computing mechanism for the specification of a cell in a piece of cell mass whose parametric representation matches or responds best to the afferent input. This cell is called the ‘winner’. (2) Control of some learning factor in the cells in the neighbourhood of the ‘winner’ so that only this neighbourhood is adapted to the current input. By virtue of the ‘neighbourhood learning,’ the SOM forms spatially ordered maps of sensory experiences, which resemble the maps observed in the brain.
The newest version of the SOM is the ASSOM (adaptive-subspace SOM). The adaptive processing units of ASSOM are able to represent signal subspaces, not just templates of the original patterns. A signal subspace is an invariance group; therefore the processing units of ASSOM are able to respond invariantly, eg to moving and transforming patterns, in a similar fashion as the complex cells in the cortex.
Get full access to this article
View all access options for this article.