3. Team year Error (top-5) AlexNet 2012 15.3% Clarifai 2013 11.2% VGG 2014 7.32% GoogLeNet 2014 6.67% ResNet 2015 3.57% ResNet+ 2016 2.99% SENet 2017 2.25% human expert 5.1% 14. • 2012年のILSVRC優勝モデル • Rectified Linear Units (ReLU) • Local Response Normalization (LRN) • Dropout(全結合層) • Pre-training(事前学習) A. Krizhevsky, "Imagenet classification with deep convolutional neural networks”, NIPS, 2012.
![MIRU2018 tutorial](https://cdn-ak-scissors.b.st-hatena.com/image/square/62a0affcc604a30f40a5042c955a04f97fcaed1d/height=288;version=1;width=512/https%3A%2F%2Fcdn.slidesharecdn.com%2Fss_thumbnails%2Fmiru2018tutorial-180805041658-thumbnail.jpg%3Fwidth%3D640%26height%3D640%26fit%3Dbounds)