Multilayer perceptrons are often trained using error backpropagation (BP). BP training can be done in either a batch or continuous manner. Claims have frequently been made that batch training is faster and/or more "correct" than continuous training because it uses a better approximation of the true gradient for its weight updates. These claims are often supported by empirical evidence on very s...

Discrete systems with long-range interactions are considered. Continuous medium models as continuous limit of discrete chain system are defined. Longrange interactions of chain elements that give the fractional equations for the medium model are discussed. The chain equations of motion with long-range interaction are mapped into the continuum equation with the Riesz fractional derivative. We fo...