Title :
Asymptotic behavior of irreducible excitatory networks of analog graded-response neurons
Author :
Pakdaman, K. ; Malta, C.P. ; Grotta-Ragazzo, C.
Author_Institution :
Dept. of Biophys. Eng., Osaka Univ., Japan
fDate :
11/1/1999 12:00:00 AM
Abstract :
In irreducible excitatory networks of analog graded-response neurons, the trajectories of most solutions tend to the equilibria. We derive sufficient conditions for such networks to be globally asymptotically stable. When the network possesses several locally stable equilibria, their location in the phase space is discussed and a description of their attraction basin is given. The results hold even when interunit transmission is delayed
Keywords :
Lyapunov methods; asymptotic stability; feedback; recurrent neural nets; analog graded-response neurons; asymptotic behavior; attraction basin; global asymptotic stability; interunit transmission; irreducible excitatory networks; locally stable equilibria; phase space; sufficient conditions; Convergence; Delay; Differential equations; Displays; Feedback loop; Joining processes; Neural networks; Neurons; Stationary state; Sufficient conditions;
Journal_Title :
Neural Networks, IEEE Transactions on
