2003 · 13 citations · 4 references
ComputingNeuroscienceMachine LearningNeural EngineeringPattern FormationNetwork TheoryNeural NetworksNeural Network ClassificationNeural Network ModelingPatternsSelf-organizing MapsSelf-organizing NetworksTopographic OrganizationTopographic RepresentationTopology Of Neural Networks
The article analyzes the relation between initial parameters setting and the formation of a topographic map of the input patterns in which the spatial locations of the neurons in the lattice are indicative of intrinsic statistical features contained in the input patterns of a Kohonen self-organizing map (SOM) algorithm. Taking a network arranged in the form of a two-dimensional lattice and trained with a two-dimensional input vector as an example, the author puts forward an initializing method for connection weights of the neurons in the competition layer.
4
Clustering of the self-organizing map
Juha Vesanto, Esa Alhoniemi · IEEE Transactions on Neural Networks · 2000 · 2.7K citations
Teuvo Kohonen · Neurocomputing · 1998 · 2K citations
Self organization of a massive document collection
Teuvo Kohonen, Samuel Kaski, Krista Lagus et al. · IEEE Transactions on Neural Networks · 2000 · 912 citations