clusteron

Blend of cluster +‎ neuron

clusteron (plural clusterons)

1. A mathematical model that represents the behavior of dendritic trees in neural networks.
   • 2000, Panayiota Poirazi, Bartlett W. Mel, “Memory Capacity of Linear vs. Nonlinear Models of Dendritic Integration”, in Sara A. Solla, Klaus-Robert Müller, Todd K. Leen, editor, Advances in Neural Information Processing Systems 12:

     The learning rule used for both cell types was similar to the "clusteron" learning rule described in (Mel, 1992a), and involved two mechanisms known to contribute to neural development:

   • 2012, Simone Fiori, Pietro Burrascano, “Polynomial Clusterons Exhibit Statistical Estimation Abilities”, in Maria Marinaro, Roberto Tagliaferri, editor, Neural Nets WIRN Vietri-99, page 113:

     The total activation value of a clusteron is computed according to the observation that it behaves as an approximative low-order polynomial function.

   • 2017, Greg Stuart, Nelson Spruston, Michael Häusser, Dendrites, page 470:

     These product terms were then summed across the dendritic tree as a whole, so that the clusteron was in effect a constrained sigma-pi unit with product terms for every pair of nearby synapses.