图 书 馆
批量归一化：通过减少内部协变量偏移加速深度网络训练Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift |
|
| 课程网址: | http://videolectures.net/icml2015_ioffe_batch_normalization/ |
| 主讲教师: | Sergey Ioffe |
| 开课单位: | 谷歌 |
| 开课时间: | 2015-12-05 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Training Deep Neural Networks is complicated by the fact that the distribution of each layer’s inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization, and in some cases eliminates the need for Dropout. Applied to a stateof-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.82\% top-5 test error, exceeding the accuracy of human raters. |
| 关 键 词: | 深度神经网络; 参数初始化; 归一化网络 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2022-11-16：chenjy |
| 最后编审: | 2022-11-16：chenjy |
| 阅读次数: | 41 |