Content deleted Content added
improve: i.consistency – i.e. correct a semantic mistake hindering the understanding that NNs and SNNs generally outperform the other a-spatial/classic and spatial statistical models in presence of non-linear relations between variables; ii.meaningfulness – i.e. consistently use the term 'a-spatial/classic' through the entire entry/article for avoiding confusions |
improve: meaningfulness – i.e. specify two hatnote templates for redirecting to 'spatial networks' or avoiding confusions about the polysemic term/abbreviation: 'SNN' Tag: Disambiguation links added |
||
Line 1:
{{Short description|Category of tailored neural networks}}
{{distinguish|Spatial network}}{{other uses|SNN (disambiguation)}}
'''Spatial neural networks''' ('''SNNs''') or '''geographically weighted neural networks''' ('''GWNNs'''), constitute a supercategory of tailored [[artificial neural networks|neural networks (NNs)]] for representing and predicting geographic phenomena. They generally improve both the statistical [[Accuracy and precision|accuracy]] and [[Statistical reliability|reliability]] of the a-spatial/classic NNs whenever they handle [[Geographic data and information|geo-spatial datasets]], and also of the other spatial [[Statistical model|(statistical) models]] (e.g. spatial regression models) whenever the geo-spatial [[data set|datasets]]' variables depict [[Nonlinear system|non-linear relations]].<ref name="Morer et al. (2020)"/><ref name="Gupta et al. (2021)"/><ref name="Hagenauer et al. (2021)"/>
| |||