The aim of the research was to find out a method of adaptive speed control, which guaranties robustness against variation of selected parameters of system like moment of inertia, time constant etc. The goal was achieved due to application of artificial neural network, which was trained on line on the base of speed control error. The work shows a structure of Artificial Neural Network (ANN), applied as adaptive speed controller, and presents an algorithm of ANN training. Some new modified versions of this algorithm were analysed and verified by simulation and experimental tests. Presented results well illustrate interestion properties of the proposed adaptive neural speed controller.