Changing Network Weights by Lie Groups
In this paper we investigate how stability properties of a continuous recursive neural network within neighbourhoods of certain equilibrium points can be changed whilst keeping the equilibrium points fixed. This can be achieved, under certain conditions, by the use of Lie group transformations operating on the synaptic weight matrix.
KeywordsVector Field Equilibrium Point Isotropy Group Group Transformation Unstable Equilibrium
Unable to display preview. Download preview PDF.