T. Kohonen

<person> A researcher at the University of Helsinki who has been studying neural networks for many years with the idea of modelling as closely as possible the behaviour of biological systems. His name is commonly associated with a particular kind of neural network in which there are only two kinds of neurons (see McCulloch-Pitts), input and others. All the input neurons are connected to all others and the others are connected only to their other nearest neighbors. The training algorithm is a relatively simple one based on the geometric layout of the neurons, and makes use of simulated annealing.

Last updated: 1994-10-19

Try this search on Wikipedia, OneLook, Google

Nearby terms:

tk « TK-90X « TK-95 « T. Kohonen » TK!Solver » TL0 » TL1

Loading