Open AccessSome new thoughts on Neural Networks with complex connection matrices
Author(s) -
M. Szilágyi,
Jens Christian Mikkelsen,
Karen Vibeke Mortensen
Publication year - 1990
Publication title -
daimi pb
Language(s) - English
Resource type - Journals
eISSN - 2245-9316
pISSN - 0105-8517
DOI - 10.7146/dpb.v19i322.6712
Subject(s) - connection (principal bundle) , artificial neural network , domain (mathematical analysis) , computer science , complex system , artificial intelligence , complex network , expression (computer science) , theoretical computer science , mathematics , geometry , mathematical analysis , world wide web , programming language
In the literature neural networks are usually understood in the domain of real activation functions and connection weights. The concept of neural networks was generalized by M. Szilagyi to include complex connections between complex units. In the present note this idea is further developed. A mathematical model is presented, an expression for the network's energy as well as a complex learning rule are proposed.