striving for simplicity:the all convolutional net

1 Why the author want to write this paper?
the basic architecture of convolutional neural networks(CNNs) mainly consists of convolutional layer, ReLU layer, pooling layer and full connection layer. In this paper, one replace the pool layer with a convolutional layer with increased stride.
2 how to write the paper?
Compared with the function of max-pooling, the author find the replacing the max-pooling with a CNN layer owns the similar function, resulting in the probability that the pooling can be removed without loss in accuracy.