Improved learning of multiple continuous trajectories with initial network state
Miroslaw Galicki, Lutz Leistritz, Herbert Witte · 2000
This study addresses a problem of learning multiple continuous trajectories by means of recurrent neural networks with (in general) time-varying weights. The learning task is transformed into an optimal control problem where both the weights and initial network state to be found are treated as controls. Based on a variational formulation of Pontryagin's maximum principle, a new learning algorithm is proposed which generalizes the one given given previously (1999). Under reasonable assumptions, its convergence is also discussed. A numerical example of learning a two-class problem is presented which demonstrates the efficiency of the approach proposed.