Abstract:\r\n\"On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.\"

Section 3.5:\r\n\"As depicted in Figure 2, the net contains eight layers with weights; the first five are convolutional and the remaining three are fully-connected. The output of the last fully-connected layer is fed to a 1000-way softmax which produces a distribution over the 1000 class labels.\"

Table 2:\r\nFor \"1 CNN\", the Top-5 (test) shows 16.4%, and for \"5 CNNs\", the Top-5 (test) also shows 16.4%.\r\n