Learn Rate Control Start Iteration

Enter the iteration number to begin Learn Rate Control (LRC). Qnet has a special algorithm to control the learning rate. This algorithm will seek the optimal learning rate range during the training run. LRC guards against divergence during training, while attempting to drive eta as high as possible. During the initial training iterations (100 would be typical) for a new network, LRC should normally be turned off. The node weights of new networks are adjusted rapidly during initial iterations and the training error can oscillate significantly. Using LRC during this period is perfectly safe, however, the LRC algorithm may drive eta unnecessarily low in an attempt to eliminate the normal startup oscillations. (See Starting New Networks).