图 书 馆
具有主动模型适应性的深度神经网络的成本效益训练Cost‑Effective Training of Deep CNNs with Active Model Adaptation |
|
| 课程网址: | http://videolectures.net/kdd2018_huang_deep_CNNs/ |
| 主讲教师: | Sheng-Jun Huang |
| 开课单位: | 南京航空航天大学 |
| 开课时间: | 2018-11-23 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Deep convolutional neural networks have achieved great success in various applications. However, training an effective DNN model for a specific task is rather challenging because it requires a prior knowledge or experience to design the network architecture, repeated trial-and-error process to tune the parameters, and a large set of labeled data to train the model. In this paper, we propose to overcome these challenges by actively adapting a pre-trained model to a new task with less labeled examples. Specifically, the pre-trained model is iteratively fine tuned based on the most useful examples. The examples are actively selected based on a novel criterion, which jointly estimates the potential contribution of an instance on optimizing the feature representation as well as improving the classification model for the target task. On one hand, the pre-trained model brings plentiful information from its original task, avoiding redesign of the network architecture or training from scratch; and on the other hand, the labeling cost can be significantly reduced by active label querying. Experiments on multiple datasets and different pre-trained models demonstrate that the proposed approach can achieve cost-effective training of DNNs. |
| 关 键 词: | 深度卷积; 神经网络; 网络架构 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2022-12-07：chenjy |
| 最后编审: | 2022-12-07：chenjy |
| 阅读次数: | 22 |