Proc. Int'l Conf. on Artificial Neural Networks, ICANN'97, Lausanne, Oct. 8-10, eds. Wulfram Gerstner, Alain Germond, Martin Hasler, and Jean-Daniel Nicoud, number 1327 in series Lecture Notes in Computer Science, publ. Springer-Verlag, Berlin, Heidelberg, pp. 243-248 (1997-10-08) (bibtex)

Objective functions for neural map formation.

Laurenz Wiskott and Terrence J. Sejnowski

Abstract: A unifying framework for analyzing models of neural map formation is presented based on growth rules derived from objective functions and normalization rules derived from constraint functions. Coordinate transformations play an important role in deriving various rules from the same function. Ten different models from the literature are classified within the objective function framework presented here. Though models may look different, they may actually be equivalent in terms of their stable solutions. The techniques used in this analysis may also be useful in investigating other types of neural dynamics.

Keywords: neural map formation, objective functions, constraints, coordinate transformations

Relevant Project:

July 1, 1997, Laurenz Wiskott,