Tuning of learning rate and momentum on back-propagation

It is known well that backpropagation is used in recognition and learning on neural networks. The backpropagation, modification of the weight is calculated by learning rate (η=0.2) and momentum (α=0.9). The number of training cycles depends on η and α, so that it is necessary to choose the most suitable values for η and α. Then, changing η and α, the authors tried to search for the most suitable values for the learning. As a result, the combination of η and α given the minimum value of the number of training cycles behave under the constant rule. Thus η=K(1-α). Moreover, the constant K is decided by the ratio between the number of output units and hidden units or the initialized weight