Neural computation and self-organizing maps: an introduction
Neural computation and self-organizing maps: an introduction
| Hi-index | 0.00 |
Brain overgrowth in early developmental stages of children with autism is well documented. This paper explores the possibility that increases in propagation delays of stimuli and the signals triggered by them, resulting from this overgrowth, may be conducive to the development of poorly structured cortical maps, which may in turn be associated with autistic characteristics. We use a framework based on Self-Organizing Maps (SOMs). Unlike the conventional SOM model that assumes that all neurons in the neighborhood of the neuron closest to a stimulus instantaneously react to it and adjust their weights, we propose a more biologically realistic model that acknowledges delays inherent in the propagation of signals. We show that propagation delays can significantly affect the performance of SOMs. Coverage of stimuli is negatively affected by either an increase in the dilution factor (a parameter in the proposed model that controls the adjustment of responses to overlapping stimuli), or a decrease in propagation speed. For large dilution factors the topological structure of the maps is also compromised. We also demonstrate the model's robustness to different input stimuli layouts and distributions.