Difference between revisions of "Self-Organizing Maps for Automated Oil-Spill Detection"
From Earth Science Information Partners (ESIP)
Carolbmeyer (talk | contribs) m (Created page with "A self-organizing map (SOM) or selforganizing feature map (SOFM) is a type of artificial neural network that is trained using unsupervised learning to produce a low-dimensional (...") |
Carolbmeyer (talk | contribs) m |
||
| Line 1: | Line 1: | ||
| + | Oleg Aulov<br> | ||
| + | <br> | ||
A self-organizing map (SOM) or selforganizing feature map (SOFM) is a type of artificial neural network that is trained using unsupervised learning to produce a low-dimensional (typically twodimensional), discretized representation of the input space of the training samples, called a map. Self-organizing maps are different from other artificial neural networks in the sense that they use a neighborhood function to preserve the topological properties of the input space. | A self-organizing map (SOM) or selforganizing feature map (SOFM) is a type of artificial neural network that is trained using unsupervised learning to produce a low-dimensional (typically twodimensional), discretized representation of the input space of the training samples, called a map. Self-organizing maps are different from other artificial neural networks in the sense that they use a neighborhood function to preserve the topological properties of the input space. | ||
Latest revision as of 09:08, December 28, 2011
Oleg Aulov
A self-organizing map (SOM) or selforganizing feature map (SOFM) is a type of artificial neural network that is trained using unsupervised learning to produce a low-dimensional (typically twodimensional), discretized representation of the input space of the training samples, called a map. Self-organizing maps are different from other artificial neural networks in the sense that they use a neighborhood function to preserve the topological properties of the input space.
