Matches in Nanopublications for { ?s ?p ?o <https://w3id.org/np/RAC7iNf2wxtsJVzmNRzEPqAQsZfO0Y8rrUufR71kvWwPY/assertion>. }
Showing items 1 to 2 of
2
with 100 items per page.
- assertion label "Citation from the paper linked in this assertion: <p>Abstract: "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."</p> <p>Section 3.5: "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."</p> <p>Table 2: For "1 CNN", the Top-5 (test) shows 16.4%, and for "5 CNNs", the Top-5 (test) also shows 16.4%. </p>" assertion.
- assertion seeAlso c399862d3b9d6b76c8436e924a68c45b-Paper.pdf assertion.