A theory for learning based on rigid bodies dynamics
Simone Fiori · IEEE Transactions on Neural Networks · 2002
A new learning theory derived from the study of the dynamics of an abstract system of masses, moving in a multidimensional space under an external force field, is presented. The set of equations describing system's dynamics may be directly interpreted as a learning algorithm for neural layers. Relevant properties of the proposed learning theory are discussed within the paper, along with results of computer simulations performed in order to assess its effectiveness in applied fields.