Файл:Network In Network.pdf

Материал из Материалы по машинному обучению
Перейти к: навигация, поиск
Network_In_Network.pdf(0 × 0 пикселей, размер файла: 581 КБ, MIME-тип: application/pdf)

MinLin1,2,QiangChen2,ShuichengYan2 1Graduate School for Integrative Sciences and Engineering 2Department of Electronic & Computer Engineering National University of Singapore, Singapore {linmin,chenqiang,eleyans}@nus.edu.sg


We propose a novel deep network structure called “Network In Network”(NIN) to enhance model discriminability for local patches within the receptive field. The conventional convolutional layer uses linear filters followed by a nonlinear activation function to scan the input. Instead, we build micro neural networks with more complex structures to abstract the data within the receptive field. We instantiate the micro neural network with a multilayer perceptron, which is a potent function approximator. The feature maps are obtained by sliding the micro networks over the input in a similar manner as CNN; they are then fed into the next layer. Deep NIN can be implemented by stacking mutiple of the above described structure. With enhanced local modeling via the micronetwork, we are able to utilize global average pooling over feature maps in the classification layer, which is easier to interpret and less prone to overfitting than traditional fully connected layers. We demonstrated the state-of-the-art classification performances with NIN on CIFAR-10 and CIFAR-100, and reasonable performances on SVHN and MNIST datasets.

История файла

Нажмите на дату/время, чтобы просмотреть, как тогда выглядел файл.

текущий16:48, 22 декабря 20160 × 0 (581 КБ)Slikos (обсуждение | вклад)
  • Вы не можете перезаписать этот файл.

Следующая 1 страница ссылается на данный файл: