During the development of deep neural networks (DNNs), it is difficult to trade off the performance of fitting ability and generalization ability in training set and unknown data (such as test set). The current solution is to reduce the complexity of the objective function, using regularization methods. In this paper, we propose a method called VOVU (Variance Of Variance of Units in the last hidden layer) to maximize the optimization of the balance between fitting power and generalization during monitoring the training process. The main idea is to give full play to the predictability of the variance of the hidden layer units in the complexity of the neural network model and use it as a generalization evaluation index. In particular, we take full advantage of the last layer of hidden layers since it has the greatest impact. The algorithm was tested on Fashion-MNIST and CIFAR-10. The experimental results demonstrate that VOVU and test loss are highly positively correlated. This implies that a smaller VOVU indicates that the network has better generalization. VOVU can serve as an alternative method for early stopping and a good predictor of the generalization performance in DNNs. Specially, when the sample size is limited, VOVU will be a better choice because it does not require dividing training data as validation set.
展开▼
