图 书 馆
Net2Net:通过知识转移加速学习Net2Net: Accelerating Learning via Knowledge Transfer |
|
| 课程网址: | http://videolectures.net/iclr2016_chen_net2net/ |
| 主讲教师: | Tianqi Chen |
| 开课单位: | 华盛顿大学 |
| 开课时间: | 2016-05-27 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We introduce techniques for rapidly transferring the information stored in one neural net into another neural net. The main purpose is to accelerate the training of a significantly larger neural net. During real-world workflows, one often trains very many different neural networks during the experimentation and design process. This is a wasteful process in which each new model is trained from scratch. Our Net2Net technique accelerates the experimentation process by instantaneously transferring the knowledge from a previous network to each new deeper or wider network. Our techniques are based on the concept of function-preserving transformations between neural network specifications. This differs from previous approaches to pre-training that altered the function represented by a neural net when adding layers to it. Using our knowledge transfer mechanism to add depth to Inception modules, we demonstrate a new state of the art accuracy rating on the ImageNet dataset. |
| 关 键 词: | 神经网络; 工作流程; 转移机制 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2023-04-16：chenxin01 |
| 最后编审: | 2023-05-21：chenxin01 |
| 阅读次数: | 21 |