图 书 馆
基于深度卷积神经网络的图像网络分类ImageNet Classification with Deep Convolutional Neural Networks |
|
| 课程网址: | http://videolectures.net/machine_krizhevsky_imagenet_classificati... |
| 主讲教师: | Alex Krizhevsky |
| 开课单位: | 多伦多大学 |
| 开课时间: | 2013-01-14 |
| 课程语种: | 英语 |
| 中文简介: |  我们训练了一个大型的深度卷积神经网络，以将LSVRC 2010 ImageNet训练中的130万个高分辨率图像分类为1000个不同的类。在测试数据上，我们实现了前1个和前5个错误率分别为39.7％和18.9％，这比以前的最新技术水平要好得多。该神经网络具有6000万个参数和500,000个神经元，由五个卷积层组成，其中一些跟在最大池化层之后，还有两个全局连接层，最后一个1000路softmax。为了使训练更快，我们使用了非饱和神经元和卷积网的非常高效的GPU实现。为了减少全局连接层中的过度拟合，我们采用了一种新的正则化方法，该方法被证明是非常有效的。 |
| 课程简介: | We trained a large, deep convolutional neural network to classify the 1.3 million high-resolution images in the LSVRC-2010 ImageNet training set into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 39.7% and 18.9% which is considerably better than the previous state-of-the-art results. The neural network, which has 60 million parameters and 500,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and two globally connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of convolutional nets. To reduce overfitting in the globally connected layers we employed a new regularization method that proved to be very effective. |
| 关 键 词: | 神经网络; 图像分辨 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-03-20：zyk |
| 最后编审: | 2021-03-20：zyk |
| 阅读次数: | 136 |