Abstract— The paper proposes a dynamic programming algorithm for training of functional networks. The algorithm considers each node as a state. The problem is formulated as find...
Emad A. El-Sebakhy, Salahadin Mohammed, Moustafa E...
— Cellular simultaneous recurrent neural network has been suggested to be a function approximator more powerful than the MLP’s, in particular for solving approximate dynamic pr...
In the framework of nonlinear process modeling, we propose training algorithms for feedback wavelet networks used as nonlinear dynamic models. An original initialization procedure...
Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like Fmeasure. Softmax-margin is a convex objecti...
Recurrent neural networks serve as black-box models for nonlinear dynamical systems identification and time series prediction. Training of recurrent networks typically minimizes t...