Export Reviews, Discussions, Author Feedback and Meta-Reviews

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. Dropout in deep neural networks is perturbing the output layer after non-linear mapping. Later it has been shown that this is closely related to perturbing the weight matrix before non-linear mapping due to the choice of mapping functions in neural networks (known as DropConnect). In a way, both Dropout and DropConnect perturb the decision boundary (ie parameter) after training, which is different from (though might be related to) perturbing the input feature vectors before training. This paper provides generalization bounds for training with perturbed features, which is more closely related to learning by feature deletion [13] or learning with corrupted features [9].