Файл:4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf

Материал из Материалы по машинному обучению
Перейти к: навигация, поиск
4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf(0 × 0 пикселей, размер файла: 1,35 МБ, MIME-тип: application/pdf)

AlexKrizhevsky University of Toronto kriz@cs.utoronto.ca IlyaSutskever University of Toronto ilya@cs.utoronto.ca GeoffreyE.Hinton University of Toronto hinton@cs.utoronto.ca

Abstract

We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. 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. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overfitting in the fully-connected layers we employed a recently-developed regularization method called “dropout” that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieve dawinning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.

История файла

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

Дата/времяРазмерыУчастникПримечание
текущий16:43, 22 декабря 20160 × 0 (1,35 МБ)Slikos (обсуждение | вклад)
  • Вы не можете перезаписать этот файл.

Следующая 1 страница ссылается на данный файл: