This paper proposes a new method to reduce training time for neural nets used as function approximators. This method relies on a geometrical control of Multilayer Perceptrons (MLP). A geometrical initialization gives first better starting points for the learning process. A geometrical parametrization achieves then a more stable convergence. During the learning process, a dynamic geometrical con...

We present gclc/Wingclc— a tool for visualizing geometrical (and not only geometrical) objects and notions, for teaching/studying mathematics, and for producing mathematical illustrations of high quality. gclc uses a language gc for declarative representation of figures and for storing mathematical contents of visual nature in textual form. In gclc, there is a build-in geometrical theorem prove...

Geometrical place can be sometimes difficult to find by applying mathematical methods. Evolutionary algorithms deal with a population of solutions. This population (initially random generated) is evolved using genetic operators. Population obtained after a specified number of iterations will contain solutions which (very likely) accomplish the geometrical place problem conditions. Geometrical p...