Electronic Resource
Springer
Circuits, systems and signal processing
12 (1993), S. 263-278
ISSN:
1531-5878
Source:
Springer Online Journal Archives 1860-2000
Topics:
Electrical Engineering, Measurement and Control Technology
Notes:
Abstract New characteristics of feedback neural networks are studied. We discuss in detail the question of updating of neurons given incomplete information about the state of the neural network. We show how the mechanism of self-indexing for such updating provides better results than assigning ‘don't know’ values to the missing parts of the state vector. Issues related to the choice of the neural model for a feedback network are also considered. Properties of a new complex valued neuron model that generalizes McCulloch-Pitts neurons are examined.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1007/BF01189877
|
Location |
Call Number |
Expected |
Availability |