Computational Differences Between
Asymmetrical and Symmetrical Networks.
Zhaoping Li Peter Dayan
Network, 10, 59-77.
Abstract
Symmetrically connected recurrent
networks have recently been used as models of a host of neural
computations. However, biological neural networks have asymmetrical
connections, at the very least because of the separat ion between
excitatory and inhibitory neurons in the brain. We study
characteristic differences between asymmetrical networks and their
symmetrical c ounterparts in cases for which they act as selective
amplifiers for particular classes of input patterns. We show that the
dramatically different dynamical beh aviours to which they have
access, often make the asymmetrical networks computationally
superior. We illustrate our results in networks that selectively
amplify oriented bars and smooth contours in visual inputs.
compressed postscript pdf