Constructions and Dynamics of Neural Networks

  • Akira Hirose
Part of the Studies in Computational Intelligence book series (SCI, volume 400)


In this chapter, we present constructions of neural networks and their dynamics in processing, learning, and self-organization. Biological neural networks, in particular, most of interface networks, evolved in such a specific manner that each network fits its particular purpose such as seeing, listening, or speaking. Artificial neural networks also possess various constructions dependent on purposes. Therefore, in this chapter, we investigate the constructions and dynamics in individual networks according to purposes. However, there exits a common dynamics in their microscopic mechanisms of learning and self-organization, namely, the Hebbian rule in the broad sense of the word. First, we consider the Hebbian rule. Then we go on to various constructions and dynamics in networks. You do not need any detailed background in advance since we begin with conventional (real-valued) neural networks and, afterward, we extend them into complex-valued neural networks (CVNNs).


Neural Network Hide Layer Input Signal Independent Component Analysis Associative Memory 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Department of Electrical EngineeringThe University of TokyoTokyoJapan

Personalised recommendations