Title :
Functional graph model of a neural network
Author :
Podolak, Igor T.
Author_Institution :
Inst. of Comput. Sci., Jagellonian Univ., Cracow, Poland
fDate :
12/1/1998 12:00:00 AM
Abstract :
A model representing neural networks is proposed. It uses the functional graphs notion defined by R. Jakubowski (1977). This is a system of nodes connected with functional edges between which binary relations can be defined. Multilayer artificial neural networks can easily be defined using functional edges to model neurons, and parametrized binary relations to model synaptic connections. Learning is also defined in terms of functional graphs. The proposed description can produce descriptions of whole classes of networks
Keywords :
feedforward neural nets; learning (artificial intelligence); binary relations; functional graph model; functional graphs; learning; multilayer artificial neural networks; neural network; parametrized binary relations; synaptic connections; Artificial neural networks; Computer architecture; Computer science; Feedforward neural networks; Feeds; Hidden Markov models; Multi-layer neural network; Neural networks; Neurons; Numerical models;
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
DOI :
10.1109/3477.735398
