A synergetic training algorithm based on potential energy function optimized

The traditional training method of synergetic neural network is to calculate prototype vector first, then adjoint vector is figured out from prototype vector according to certain rules, the whole course is slowly. The studying of potential energy function dynamics process can train prototype vector and adjoint vector meanwhile. The optimization approach is introduced to synergetic dynamics evolution process, using the memory gradient algorithm instead of the steepest gradient algorithm to optimize the potential energy function, experiment result on cell images recognition shows that the new algorithm can effectively search the prototype vector and adjoint vector meanwhile, and excellent, correct and fast recognition result show the new algorithm is more available than traditional training method.